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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53534
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the start of a document or text section

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

    AM and became $

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.73
     oprot
    -0.68
    windowFixed
    -0.67
     AssemblyCulture
    -0.66
     resourceCulture
    -0.66
    +#+#
    -0.65
    原始内容存档于
    -0.64
     متعلقه
    -0.62
    Eloquent
    -0.61
     typelib
    -0.60
    POSITIVE LOGITS
    AutoModerator
    0.60
    neux
    0.60
    utuhkan
    0.59
    </tfoot>
    0.56
     Twisted
    0.56
    (;;)
    0.55
    }*/
    
    0.55
    }}">
    0.55
    edicated
    0.53
    doria
    0.53
    Activations Density 0.199%

    No Known Activations