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. 12428
    Prev
    Next
    INDEX
    Explanations

    URLs and web links in the text

    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
    styleUrls
    -0.70
     LUMP
    -0.67
     Anak
    -0.66
    BASEPATH
    -0.65
    Anak
    -0.64
    horizontalLayout
    -0.61
     itſelf
    -0.61
     kör
    -0.60
    Gentlemen
    -0.60
    tudi
    -0.58
    POSITIVE LOGITS
    ://
    3.01
    ://"
    1.81
    ="//
    1.35
    :///
    1.22
    :\/\/
    1.20
    ://$
    1.13
    www
    1.06
    ">//
    0.92
    :/
    0.90
    Composable
    0.86
    Activations Density 0.042%

    No Known Activations