Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 12513
    Prev
    Next
    INDEX
    Explanations

    elements related to community involvement and participation

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

    Followed by an infinitive

    np_acts-logits-general · gemini-2.0-flash

    to summarize, elucidate, determine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     informée
    -0.78
     olvido
    -0.64
     MainAxisSize
    -0.63
     BoxFit
    -0.60
     tarko
    -0.59
     avoient
    -0.58
    Дереккөздер
    -0.58
     esfuer
    -0.57
    rzost
    -0.56
    Jereo
    -0.56
    POSITIVE LOGITS
    $")
    0.39
    >';
    
    0.37
    featureID
    0.36
    /#{
    0.35
    =\""
    0.35
    citenamefont
    0.34
     ""}
    0.34
    --]
    0.34
     ''}
    0.34
    \"");
    0.33
    Activations Density 0.976%

    No Known Activations