© 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. 83065
    Prev
    Next
    INDEX
    Explanations

    patterns and structures in code

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

    mathematical calculations and code definitions

    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
     autorytatywna
    -1.16
    Personendaten
    -1.01
    transQ
    -0.81
    oa̍t
    -0.78
     Biôgrafia
    -0.78
    httphttps
    -0.77
     EconPapers
    -0.76
    EDEFAULT
    -0.73
     kasarigan
    -0.72
     betweenstory
    -0.72
    POSITIVE LOGITS
     also
    0.36
     Say
    0.35
     la
    0.35
     Sar
    0.34
     present
    0.34
    <%=
    0.34
     Volk
    0.33
     over
    0.33
     always
    0.33
    :
    0.32
    Activations Density 0.049%

    No Known Activations