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. 18-GEMMASCOPE-RES-16K
    6. 10241
    Prev
    Next
    INDEX
    Explanations

    high numerical values associated with statistical or algorithmic data attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    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
    WithIdentifier
    -0.58
     himo
    -0.57
    principalColumn
    -0.56
    RenderAtEndOf
    -0.56
    __[
    -0.54
    Portale
    -0.54
    EndContext
    -0.54
    asInstanceOf
    -0.53
    mény
    -0.49
    POSITIVE LOGITS
    ())));
    0.59
    manteau
    0.57
     مشين
    0.57
    ')}}
    0.56
    Билгалдахарш
    0.52
     }))
    0.50
    rungsseite
    0.50
    ASSE
    0.49
     )))
    0.48
    insics
    0.48
    Activations Density 0.019%

    No Known Activations