© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 4472
    Prev
    Next
    INDEX
    Explanations

    terms related to technical specifications and components in telecommunications and electronics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    extAlignment
    -0.79
    setCellValue
    -0.70
    IVEREF
    -0.69
    IntoConstraints
    -0.66
    Morfologia
    -0.62
    omitempty
    -0.57
    ConstraintMaker
    -0.56
    enaam
    -0.56
    UnknownFields
    -0.55
    Trainer
    -0.55
    POSITIVE LOGITS
    NgModule
    0.66
    ांकि
    0.56
    Datuak
    0.56
     NDEBUG
    0.56
    further
    0.54
     vidare
    0.53
     Einfluß
    0.52
    Portale
    0.52
    cesi
    0.51
    avantage
    0.51
    Activations Density 4.901%

    No Known Activations