© 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. 23-GEMMASCOPE-RES-16K
    11. 6165
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal charges and detentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.68
     AssemblyCulture
    -0.66
     ***!
    -0.64
     AssemblyProduct
    -0.60
    migrationBuilder
    -0.60
     />';
    -0.59
    nodoc
    -0.57
     &___
    -0.56
    PhysRev
    -0.56
    ScopeManager
    -0.55
    POSITIVE LOGITS
     charges
    0.93
     charge
    0.89
    Charges
    0.71
     Charges
    0.71
    charges
    0.70
     Charge
    0.69
    charge
    0.68
    Charge
    0.68
     charged
    0.64
     CHARGE
    0.64
    Activations Density 0.333%

    No Known Activations