© 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. 543
    Prev
    Next
    INDEX
    Explanations

    technical specifications and measurements in data-related contexts

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

    Code, numbers, and uncommon symbols

    np_acts-logits-general · gemini-2.0-flash

    technical terms and code

    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
     ModelExpression
    -0.74
     мәкал
    -0.60
     disambiguazione
    -0.59
     numberOfRows
    -0.57
     extranjera
    -0.56
     salvaje
    -0.54
     propOrder
    -0.53
    awtextra
    -0.53
     metav
    -0.53
     resourceCulture
    -0.52
    POSITIVE LOGITS
    fromnode
    0.59
    transQ
    0.53
     nonUne
    0.52
     הר
    0.40
    handleDelete
    0.38
    Apoll
    0.36
    orderby
    0.36
    helloworld
    0.36
    ammans
    0.36
     Montal
    0.35
    Activations Density 0.904%

    No Known Activations