© 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. 14709
    Prev
    Next
    INDEX
    Explanations

    terms related to measurement and classification in scientific contexts

    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
     décédé
    -0.70
     mga
    -0.62
     survie
    -0.61
     kollu
    -0.61
    ágok
    -0.60
     omissions
    -0.58
     saddest
    -0.58
     deficiencies
    -0.57
     autres
    -0.57
     colère
    -0.57
    POSITIVE LOGITS
    PerformLayout
    0.87
    __':
    0.80
     resourceCulture
    0.69
    __":
    0.68
    typeorm
    0.68
    yargs
    0.65
    parsedMessage
    0.64
     vPvB
    0.64
    awtextra
    0.63
    exitRule
    0.61
    Activations Density 2.810%

    No Known Activations