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. 1326
    Prev
    Next
    INDEX
    Explanations

    the beginning of new documents or sections

    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
     CreateTagHelper
    -1.09
    tagHelperRunner
    -0.99
    ValueStyle
    -0.85
    ViewFeatures
    -0.82
    jspb
    -0.77
     ModelExpression
    -0.77
     unknownFields
    -0.74
     tartalomajánló
    -0.67
    AccessorTable
    -0.67
    ReadKey
    -0.67
    POSITIVE LOGITS
     [
    0.86
    </em>
    0.82
    </i>
    0.75
    ,”
    0.72
    ,"
    0.70
    !”
    0.70
    !"
    0.67
    ”
    0.65
    "
    0.65
    .”
    0.64
    Activations Density 0.425%

    No Known Activations