Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 12937
    Prev
    Next
    INDEX
    Explanations

    references to banks or banking institutions

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

    bank of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    凝土
    -0.39
    ocardio
    -0.37
    Coro
    -0.37
    liferay
    -0.36
    Composable
    -0.34
    TacToe
    -0.34
     المعيارى
    -0.34
     ModelRenderer
    -0.33
    ragalactic
    -0.33
    цездатний
    -0.33
    POSITIVE LOGITS
     BANK
    0.59
    ruptcy
    0.56
    BANK
    0.56
    Bank
    0.54
     Banker
    0.52
     "..\..\
    0.51
     Bank
    0.51
    TabIndex
    0.50
    rupt
    0.50
     برانيه
    0.49
    Activations Density 0.008%

    No Known Activations