© 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. 107296
    Prev
    Next
    INDEX
    Explanations

    references to documents and data structures related to subscriptions and contexts

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

    document identifiers

    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
     is
    -0.30
     half
    -0.27
     
    -0.26
     according
    -0.25
     very
    -0.25
     will
    -0.25
     showing
    -0.25
     Clements
    -0.25
     such
    -0.24
     According
    -0.24
    POSITIVE LOGITS
    Diweddarwch
    0.77
     BoxFit
    0.77
    <unused14>
    0.76
    expandindo
    0.76
    <unused28>
    0.75
    [@BOS@]
    0.75
    <unused41>
    0.75
    <unused51>
    0.75
    <unused16>
    0.75
    <unused3>
    0.75
    Activations Density 0.006%

    No Known Activations