© 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. 11560
    Prev
    Next
    INDEX
    Explanations

    exception handling keywords in programming

    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
    bewerken
    -0.55
     I
    -0.54
     M
    -0.53
    iNdEx
    -0.51
     Pal
    -0.51
     ());
    -0.49
     LOT
    -0.49
    }{*}{
    -0.48
    </strong>
    -0.48
     spot
    -0.48
    POSITIVE LOGITS
    throw
    1.35
    VIAF
    1.00
     Throw
    1.00
     throw
    0.96
    unhofer
    0.95
     Throws
    0.94
    Throw
    0.89
    __*/
    0.86
    Hozzáférés
    0.85
     Throwing
    0.83
    Activations Density 0.012%

    No Known Activations