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. 13631
    Prev
    Next
    INDEX
    Explanations

    keywords related to community, collaboration, and interpersonal relationships

    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
    ChildScrollView
    -0.81
    Portale
    -0.73
     estekak
    -0.72
     doInBackground
    -0.72
    FormTagHelper
    -0.71
     pleaſure
    -0.67
     purpoſe
    -0.67
     viewType
    -0.66
     autorytatywna
    -0.64
    </tfoot>
    -0.60
    POSITIVE LOGITS
     internal
    0.88
    internal
    0.86
    Internal
    0.81
     domestic
    0.80
     internally
    0.79
     Internal
    0.77
     intra
    0.76
    Domestic
    0.76
    domestic
    0.75
     Intra
    0.74
    Activations Density 0.365%

    No Known Activations