© 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. 24-GEMMASCOPE-RES-16K
    11. 13736
    Prev
    Next
    INDEX
    Explanations

    references to mathematical or scientific concepts and parameters related to data

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

    Numbers, often zero or close to zero

    np_acts-logits-general · gemini-2.0-flash

    zero and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NameInMap
    -0.51
     مشين
    -0.50
    AccessFile
    -0.46
    fastjson
    -0.46
    RenderAtEndOf
    -0.45
    igslist
    -0.45
    endsection
    -0.42
    plish
    -0.42
    írus
    -0.42
    קישורים
    -0.42
    POSITIVE LOGITS
    0
    1.50
    ０
    0.90
    ০
    0.79
    ۰
    0.75
     myſelf
    0.74
     zéro
    0.71
     itſelf
    0.71
     zero
    0.70
     raiſ
    0.66
    𝟎
    0.66
    Activations Density 0.619%

    No Known Activations