© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 120224
    Prev
    Next
    INDEX
    Explanations

    references to sources or citations

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

    source code

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     CreateTagHelper
    -0.72
    MigrationBuilder
    -0.54
    PreferredItem
    -0.52
     Taktlose
    -0.47
    SaveChangesAsync
    -0.45
     Infórmanos
    -0.45
    afficheront
    -0.45
    nloa
    -0.44
    rawDesc
    -0.44
     defaultstate
    -0.44
    POSITIVE LOGITS
    source
    3.28
     source
    3.23
    Source
    2.70
     Source
    2.69
     SOURCE
    2.50
     sources
    2.41
    SOURCE
    2.31
    sources
    2.19
     fuente
    2.14
    ource
    2.08
    Activations Density 0.009%

    No Known Activations