© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 5567
    Prev
    Next
    INDEX
    Explanations

    specificity in product features and availability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases related to movement, travel, or transportation.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    phrases that convey process or progression—linking actions by cause, result, direction, or method—especially in formal or technical descriptions.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    words that signal continuation, progression, or causal relationships in narrative or technical sequences.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    currentColor
    -0.62
     виправивши
    -0.50
    webElementGuid
    -0.46
    下载附件
    -0.43
    <>
    -0.41
    webElementXpaths
    -0.41
    nodoc
    -0.41
     gyhoeddwyd
    -0.40
     Normdatei
    -0.39
    ValueStyle
    -0.39
    POSITIVE LOGITS
     betweenstory
    0.72
     intptr
    0.66
    colgante
    0.56
    .*")]
    0.51
    AnchorStyles
    0.49
     wikipagina
    0.49
    hynch
    0.49
     Referenzen
    0.48
    caneca
    0.47
    pyrid
    0.47
    Activations Density 1.221%

    No Known Activations