© 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. 16-GEMMASCOPE-RES-16K
    6. 8766
    Prev
    Next
    INDEX
    Explanations

    various forms of the sequence of hyphens

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

    Diff commands

    np_acts-logits-general · gemini-2.0-flash

    git diff commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fap
    -0.74
    epam
    -0.73
     RSC
    -0.72
     Weh
    -0.71
     VPC
    -0.70
    ECH
    -0.70
     PAH
    -0.70
     PIS
    -0.68
    ль
    -0.68
     húmedo
    -0.67
    POSITIVE LOGITS
     --
    0.90
     -->
    0.89
    VIAF
    0.88
    awtextra
    0.85
    memberOf
    0.81
     ->
    0.81
     Osbourne
    0.80
    ><!--
    0.79
    //--
    0.78
     ##
    0.75
    Activations Density 0.107%

    No Known Activations