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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1300
    Prev
    Next
    INDEX
    Explanations

    conversational cues and expressions of uncertainty

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

    Follows a comma or quotation mark

    np_acts-logits-general · gemini-2.0-flash

    comparison and dependencies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     ***!
    -0.72
    الحياه
    -0.68
     defaultstate
    -0.65
    uxxxx
    -0.65
     Signalez
    -0.63
    ValueStyle
    -0.62
    Geplaatst
    -0.59
    RTCK
    -0.55
    ViewImports
    -0.55
    下载附件
    -0.53
    POSITIVE LOGITS
     Red
    0.47
     Core
    0.47
     nahilalakip
    0.46
    aktur
    0.45
    ABUL
    0.43
    Red
    0.43
     Armour
    0.43
     Corn
    0.42
     Forest
    0.41
     Cornwall
    0.41
    Activations Density 1.235%

    No Known Activations