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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 6144
    Prev
    Next
    INDEX
    Explanations

    bullet points and key highlights in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ILayout
    -0.59
    قایناق‌لار
    -0.52
    henswürdigkeiten
    -0.51
    orance
    -0.51
    ooplankton
    -0.50
    理石
    -0.50
     Tans
    -0.50
    徨
    -0.49
    ⦒
    -0.49
     zeitung
    -0.49
    POSITIVE LOGITS
     •
    1.56
    ••
    1.34
    •••
    1.29
    •
    1.27
    .•
    1.25
    ••••
    1.23
    )•
    1.16
     ••
    1.11
    ~•
    1.05
    €¢
    0.90
    Activations Density 0.170%

    No Known Activations