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 - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 43184
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving variables and operations

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    .
    -0.60
     r
    -0.49
    ...
    -0.49
     </
    -0.48
    -
    -0.46
    </
    -0.45
     She
    -0.44
    )
    -0.44
     gr
    -0.42
    ↵↵
    -0.42
    POSITIVE LOGITS
     '\\;'
    1.17
     ویکی‌پدیا
    1.05
    expandindo
    1.05
    oa̍t
    1.01
     كومونز
    0.96
    IsMutable
    0.94
     unknownFields
    0.93
    Revenir
    0.91
    neſs
    0.90
     myſelf
    0.90
    Activations Density 0.336%

    No Known Activations