© 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
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 8980
    Prev
    Next
    INDEX
    Explanations

    commands related to identity and control operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.55
    |};
    -0.52
    BeginContext
    -0.52
    PreInfinity
    -0.52
    bootstrapcdn
    -0.51
     impro
    -0.48
    addPreferredGap
    -0.48
     Angle
    -0.47
    transQ
    -0.46
     Alg
    -0.45
    POSITIVE LOGITS
    aarrggbb
    0.45
     piş
    0.40
     düş
    0.40
     varanda
    0.39
     سبورت
    0.38
     kawaida
    0.38
    EDEFAULT
    0.38
     ceinture
    0.37
     vrijwilli
    0.37
     tilbake
    0.37
    Activations Density 0.186%

    No Known Activations