© 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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 13924
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries regarding programming or technical advice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
     investigação
    -0.46
    Portály
    -0.41
    Interviewer
    -0.39
    ctivité
    -0.36
     semula
    -0.36
     nämlich
    -0.35
     Einführung
    -0.35
     operações
    -0.35
     saus
    -0.35
    IMPORTED
    -0.34
    POSITIVE LOGITS
     linkovi
    0.49
    zzleHttp
    0.48
    verwijspagina
    0.47
    ?</
    0.47
    ??)
    0.47
    ???
    0.45
     ?</
    0.45
     surla
    0.44
    ??
    0.44
    ?',
    0.44
    Activations Density 1.114%

    No Known Activations