© 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
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 8291
    Prev
    Next
    INDEX
    Explanations

    comments or statements that express criticism or dissent regarding societal issues

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

    Token followed by a quotation mark or letter

    np_acts-logits-general · gemini-2.0-flash

    race and justice system

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     usaha
    -0.36
     veden
    -0.35
     mengin
    -0.32
     megt
    -0.32
     přij
    -0.32
    Bibliograf
    -0.32
     confiança
    -0.32
     miembros
    -0.31
     poved
    -0.31
    場合
    -0.31
    POSITIVE LOGITS
    IUrlHelper
    0.69
     Infórmanos
    0.63
     الحره
    0.63
     ModelExpression
    0.58
     AssemblyProduct
    0.58
    MigrationBuilder
    0.58
    @
    0.58
    DebuggerNonUser
    0.58
    Typo
    0.57
    Anon
    0.57
    Activations Density 0.429%

    No Known Activations