© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 55036
    Prev
    Next
    INDEX
    Explanations

    special formatting or markup in the text

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

    <b></b> * formatting

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    httphttps
    -0.66
    twimg
    -0.63
    InitVars
    -0.59
     defaultstate
    -0.58
     gynhyrchwyd
    -0.58
    rawDesc
    -0.58
    AndEndTag
    -0.57
     ويكيميديا
    -0.57
     initComponents
    -0.53
    ########.
    -0.53
    POSITIVE LOGITS
     positive
    0.41
    multiplier
    0.35
     negative
    0.34
    boxed
    0.33
    positive
    0.32
     positiva
    0.32
    didSet
    0.32
     diſt
    0.32
     unſ
    0.32
     ſte
    0.32
    Activations Density 0.069%

    No Known Activations