© 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. 120328
    Prev
    Next
    INDEX
    Explanations

    statements indicating consistency or agreement in research findings

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

    consistent with

    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
     eût
    -0.54
    principalColumn
    -0.52
     navideña
    -0.51
     touristique
    -0.51
    InjectAttribute
    -0.50
     mourut
    -0.50
     iNdEx
    -0.49
     Moscú
    -0.49
     ainfi
    -0.48
    DeleteBehavior
    -0.48
    POSITIVE LOGITS
     sp
    0.39
     Tend
    0.36
     pe
    0.35
    ContentAlignment
    0.35
     Bs
    0.35
     مشين
    0.34
     Tk
    0.34
     tenders
    0.34
     Fork
    0.34
     thereon
    0.34
    Activations Density 0.440%

    No Known Activations