© 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. 12-GEMMASCOPE-RES-16K
    11. 3159
    Prev
    Next
    INDEX
    Explanations

    phrases indicating generated or auto-generated code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    providedIn
    -0.79
    GenerationType
    -0.76
    IntoConstraints
    -0.76
     GenerationType
    -0.71
    BASEPATH
    -0.65
    aarrggbb
    -0.64
    ="@+
    -0.64
    UrlEncoded
    -0.63
    stateProvider
    -0.63
    onViewCreated
    -0.63
    POSITIVE LOGITS
    DebuggerNonUser
    0.32
     écl
    0.32
    mstyle
    0.32
     géné
    0.31
    Pyx
    0.30
     stork
    0.30
    analyst
    0.29
     analyst
    0.28
     рели
    0.28
    ASYNC
    0.28
    Activations Density 0.515%

    No Known Activations