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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 19-GEMMASCOPE-RES-16K
    6. 2152
    Prev
    Next
    INDEX
    Explanations

    specific medical terms or phrases related to endoscopic procedures and endocrine-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.91
    хьтан
    -0.86
     Lightboxes
    -0.78
    Revenir
    -0.77
     Roskov
    -0.77
    MessageOf
    -0.74
    UserScript
    -0.74
    InjectAttribute
    -0.71
    +#+#
    -0.71
     DataTypes
    -0.70
    POSITIVE LOGITS
     End
    0.96
     END
    0.91
    End
    0.80
     end
    0.78
    ToEnd
    0.73
    END
    0.66
    orses
    0.64
    eavor
    0.61
    setEnd
    0.61
     user
    0.58
    Activations Density 0.193%

    No Known Activations