© 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. 8095
    Prev
    Next
    INDEX
    Explanations

    numerical values with varying degrees of emphasis or importance

    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
     itſelf
    -2.21
     myſelf
    -2.10
     Efq
    -1.95
     Monfieur
    -1.92
     Jefus
    -1.89
     Theſe
    -1.87
     doubtnut
    -1.79
     ―――――
    -1.77
     ſeveral
    -1.76
     themſelves
    -1.73
    POSITIVE LOGITS
    ,
    1.18
    ↵↵
    1.12
     in
    1.12
    .
    1.06
     (
    1.04
     a
    1.02
     to
    1.02
     I
    1.01
     is
    0.99
     "
    0.99
    Activations Density 0.700%

    No Known Activations