© 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-2-9B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 13223
    Prev
    Next
    INDEX
    Explanations

    keywords related to scientific terminology and research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.93
    oa̍t
    -0.84
    Autoritní
    -0.79
     resourceCulture
    -0.78
    WithIOException
    -0.78
     ब्रेकडाउन
    -0.77
    styleType
    -0.77
    Personendaten
    -0.75
    ViewImports
    -0.74
    principalColumn
    -0.73
    POSITIVE LOGITS
     ocurrido
    0.35
    etera
    0.30
     expuesto
    0.28
     acompaña
    0.28
     scénario
    0.28
     Keuangan
    0.27
     exista
    0.27
    .
    0.27
     herum
    0.27
     campañas
    0.27
    Activations Density 0.426%

    No Known Activations