© 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-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 10912
    Prev
    Next
    INDEX
    Explanations

    technical terms related to API, data management, and structured resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 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
    hematical
    -0.89
    intenance
    -0.87
    æa
    -0.85
    orithm
    -0.83
    duled
    -0.83
    ratulations
    -0.80
    unicip
    -0.79
    litude
    -0.78
    pectives
    -0.78
    erapeutic
    -0.77
    POSITIVE LOGITS
    on
    0.55
    g
    0.55
    est
    0.54
    om
    0.52
    in
    0.52
    un
    0.51
    ss
    0.49
    ni
    0.49
    um
    0.48
    es
    0.48
    Activations Density 0.303%

    No Known Activations