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

    Neuronpedia

    APICircuit 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. 12-GEMMASCOPE-RES-16K
    6. 1655
    Prev
    Next
    INDEX
    Explanations

    the beginning of a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __':
    
    -0.93
    __':
    -0.84
    SourceChecksum
    -0.78
    oudoune
    -0.78
    脚注の使い方
    -0.77
    __":
    
    -0.75
    rungsseite
    -0.72
     tartalomajánló
    -0.72
    ValueStyle
    -0.71
    RenderAtEndOf
    -0.71
    POSITIVE LOGITS
     AssemblyCulture
    0.52
     primas
    0.48
    true
    0.45
    passing
    0.43
    Passing
    0.40
     scomp
    0.39
    unstable
    0.39
    died
    0.39
     fays
    0.39
    而非
    0.39
    Activations Density 0.037%

    No Known Activations