© 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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10852
    Prev
    Next
    INDEX
    Explanations

    references to API and repository patterns in code

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

    Code snippets or programming terms

    np_acts-logits-general · gemini-2.0-flash

    code keywords and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 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
    FormTagHelper
    -0.97
    SequentialGroup
    -0.85
    MigrationBuilder
    -0.80
    principalTable
    -0.78
     StatefulWidget
    -0.73
     GenerationType
    -0.72
    IUrlHelper
    -0.72
     CreateTagHelper
    -0.72
    TagHelper
    -0.71
    DeleteBehavior
    -0.71
    POSITIVE LOGITS
    ecma
    0.31
     eben
    0.29
     ıs
    0.28
     HARRIS
    0.28
     reales
    0.27
    Wieder
    0.27
    >';
    
    0.27
     tejido
    0.25
     cortes
    0.25
     unicornio
    0.25
    Activations Density 0.487%

    No Known Activations