Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 4473
    Prev
    Next
    INDEX
    Explanations

    code constructs related to data manipulation and type conversion in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code-related tokens and characters

    np_acts-logits-general · gemini-2.0-flash

    documentation comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IContainer
    -0.69
    LookAnd
    -0.68
     Seeder
    -0.67
    PerformLayout
    -0.67
    ConstraintMaker
    -0.64
    Personensuche
    -0.63
    IsContent
    -0.62
    AutoScaleMode
    -0.61
    ClientSize
    -0.61
    Ārējās
    -0.59
    POSITIVE LOGITS
    See
    0.62
    ]</
    0.56
    )<
    0.54
     See
    0.53
    .<
    0.52
     }</
    0.50
    .</
    0.50
    }}/>
    0.50
    vesse
    0.49
    }</
    0.48
    Activations Density 0.127%

    No Known Activations