© 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 - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 68518
    Prev
    Next
    INDEX
    Explanations

    references to graphic-related packages in LaTeX documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    Fres
    -0.32
     El
    -0.32
    Respuesta
    -0.31
     komma
    -0.30
     Can
    -0.29
     can
    -0.29
    tfrac
    -0.28
    FieldNumber
    -0.28
     suk
    -0.28
     Dew
    -0.28
    POSITIVE LOGITS
    graphicx
    4.97
    MemoryWarning
    0.86
     للاسماء
    0.83
     HasFactory
    0.83
    UrlResolution
    0.82
    WithIOException
    0.81
    uxxxx
    0.77
    istoitu
    0.74
    zzleHttp
    0.74
     AssemblyTitle
    0.71
    Activations Density 0.000%

    No Known Activations