© 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. 9114
    Prev
    Next
    INDEX
    Explanations

    terms related to hybrid entities or concepts

    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
     itſelf
    -1.02
     whoſe
    -0.93
     Theſe
    -0.92
     doubtnut
    -0.90
     Efq
    -0.90
     Jefus
    -0.90
    ^(@)
    -0.87
     resourceCulture
    -0.86
     leaſt
    -0.86
     ་་
    -0.85
    POSITIVE LOGITS
     However
    0.80
    ule
    0.77
    ular
    0.74
     
    0.64
    bar
    0.62
    var
    0.62
    ULE
    0.62
     But
    0.61
     pro
    0.60
     I
    0.59
    Activations Density 0.171%

    No Known Activations