© 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. 9-GEMMASCOPE-RES-16K
    11. 8155
    Prev
    Next
    INDEX
    Explanations

    hashtags and other identifiers related to code or structured data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/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.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    دانشنامهٔ
    -0.67
    InvalidProtocol
    -0.65
    RunAsync
    -0.61
    PARTIC
    -0.60
    الحياه
    -0.58
     betweenstory
    -0.57
    aarrggbb
    -0.55
    ozat
    -0.53
     سكانية
    -0.52
     automata
    -0.52
    POSITIVE LOGITS
    ;->
    0.82
     #
    0.78
    WithMany
    0.68
    BeginContext
    0.67
    setof
    0.66
     Вікі
    0.64
    writerow
    0.62
     snippetHide
    0.61
    antMatchers
    0.61
    <h1>
    0.61
    Activations Density 0.021%

    No Known Activations