© 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. 21-GEMMASCOPE-RES-16K
    11. 2142
    Prev
    Next
    INDEX
    Explanations

    a specific structure or formatting in a text, as indicated by its activation of certain tokens

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    classID
    -0.54
    usercontent
    -0.52
    SourceChecksum
    -0.51
    hable
    -0.48
    出版年
    -0.47
    orship
    -0.47
     calendriers
    -0.46
     diesmal
    -0.45
     chup
    -0.45
    chable
    -0.45
    POSITIVE LOGITS
    mybatisplus
    0.69
    SysUser
    0.58
    =#{
    0.56
    verwijspagina
    0.56
     JSONObject
    0.55
    <>());
    0.55
    Scalars
    0.54
    /${
    0.53
     #{
    0.52
     disambiguazione
    0.52
    Activations Density 0.034%

    No Known Activations