Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 34-GEMMASCOPE-RES-16K
    6. 11560
    Prev
    Next
    INDEX
    Explanations

    phrases related to research methodologies and participant data collection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الرياضيه
    -0.50
     AssemblyCompany
    -0.47
     Grüsse
    -0.45
     zijne
    -0.44
    inaison
    -0.40
     виправивши
    -0.39
    Gambas
    -0.39
    setVerticalGroup
    -0.39
    órico
    -0.37
     réparer
    -0.36
    POSITIVE LOGITS
     survey
    2.95
     surveys
    2.63
     Survey
    2.53
    survey
    2.50
    Survey
    2.47
     surveyed
    2.42
     Surveys
    2.25
     SURVEY
    2.22
    Surveys
    2.14
     encuesta
    2.11
    Activations Density 0.663%

    No Known Activations