© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 15087
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences or instructions

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

    First character or short word

    np_acts-logits-general · gemini-2.0-flash

    Russian, German, French, Spanish, English fragments

    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
     AssemblyCulture
    -1.08
    ImageContext
    -1.04
     Efq
    -1.04
     فريبيس
    -0.97
    NUMX
    -0.95
    tvguidetime
    -0.95
     ddelweddau
    -0.93
    IntoConstraints
    -0.92
     lenker
    -0.90
     itſelf
    -0.87
    POSITIVE LOGITS
    '
    0.55
     is
    0.52
    br
    0.48
    ’
    0.47
     also
    0.47
    let
    0.46
     let
    0.45
    In
    0.45
    ↵↵
    0.45
    j
    0.45
    Activations Density 0.101%

    No Known Activations