© 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. 0-GEMMASCOPE-RES-16K
    11. 8316
    Prev
    Next
    INDEX
    Explanations

    dates and numbers that indicate time periods or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     protoimpl
    -0.68
    NameInMap
    -0.68
     ddelweddau
    -0.66
    ]}"
    -0.62
    ')}}"
    -0.58
    لينكات
    -0.57
    Véxase
    -0.56
     pinulongan
    -0.55
    )))));
    -0.55
    ‚¬
    -0.54
    POSITIVE LOGITS
     Monfieur
    0.79
    CloseOperation
    0.69
     Shakspeare
    0.61
    HttpFoundation
    0.61
     Cæsar
    0.58
     Poincaré
    0.58
     Haga
    0.58
     ſever
    0.57
    giveness
    0.56
     plagioclase
    0.56
    Activations Density 0.239%

    No Known Activations