© 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. 1-GEMMASCOPE-RES-16K
    11. 13888
    Prev
    Next
    INDEX
    Explanations

    references to linking and connectivity, especially in relation to networks and data transmission

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Majefty
    -0.73
     leaſt
    -0.69
     uſed
    -0.66
     Monfieur
    -0.64
     poffible
    -0.64
     isNameExpr
    -0.62
     noft
    -0.61
     Cæsar
    -0.61
     fhew
    -0.60
     becauſe
    -0.60
    POSITIVE LOGITS
    Билгалдахарш
    0.62
    ConstraintMaker
    0.60
     connections
    0.59
    });
    0.58
    includegraphics
    0.56
    ldquo
    0.54
    ()}}
    0.53
     connection
    0.52
    大利
    0.52
    urto
    0.51
    Activations Density 0.511%

    No Known Activations