© 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. 25-GEMMASCOPE-RES-16K
    11. 5429
    Prev
    Next
    INDEX
    Explanations

    references to "record" and its variations, indicating it is focused on documenting or maintaining information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Искәрмәләр
    -0.61
     ​​
    -0.55
    rzost
    -0.54
    peted
    -0.53
     McCann
    -0.49
    ývá
    -0.48
     Mott
    -0.48
     referenties
    -0.48
    addWidget
    -0.47
    раздо
    -0.47
    POSITIVE LOGITS
    keeping
    0.96
    atorios
    0.73
    breaking
    0.72
     keeping
    0.72
    keeper
    0.69
    Keeping
    0.69
     Keeping
    0.68
     breaking
    0.68
    KEEP
    0.67
    ApiModelProperty
    0.66
    Activations Density 0.174%

    No Known Activations