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. 112
    Prev
    Next
    INDEX
    Explanations

    verbs or phrases that indicate changes or transformations over time

    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
    المشاركات
    -0.60
    AlterField
    -0.58
    UnusedPrivate
    -0.57
    렀
    -0.56
    bitField
    -0.55
    <>("
    -0.54
    noOf
    -0.54
     Canary
    -0.54
    =$?
    -0.53
    WSGI
    -0.53
    POSITIVE LOGITS
    AnchorStyles
    0.78
     out
    0.74
     in
    0.70
     up
    0.69
     from
    0.67
    ขึ้น
    0.67
     across
    0.61
     beyond
    0.60
    seamnă
    0.59
     ashore
    0.59
    Activations Density 0.475%

    No Known Activations