© 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
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 15285
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical modeling and estimation techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     per
    -0.32
    posten
    -0.28
     principes
    -0.27
     ética
    -0.26
    stdbool
    -0.26
     social
    -0.26
     actes
    -0.25
     bukit
    -0.25
     nadal
    -0.25
     Luisa
    -0.25
    POSITIVE LOGITS
    MigrationBuilder
    0.75
     ModelExpression
    0.74
     AssemblyTitle
    0.74
     CreateTagHelper
    0.73
     surla
    0.72
     resourceCulture
    0.68
     pinulongan
    0.65
     informée
    0.65
    errHandler
    0.62
    CodeAttribute
    0.61
    Activations Density 1.355%

    No Known Activations