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 Post
    5. 12-GEMMASCOPE-RES-1M
    6. 37
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to function controllers in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    1,048,576
    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
    TypedDataSet
    -0.53
    tagHelper
    -0.47
    {#
    -0.47
    AndEndTag
    -0.46
     belleza
    -0.45
    ELEMENTS
    -0.44
    ORAGE
    -0.44
     potenza
    -0.44
     نعم
    -0.44
    Descripció
    -0.44
    POSITIVE LOGITS
    ftagPool
    0.68
    MLLoader
    0.66
     Chwiliwch
    0.65
    ReusableCell
    0.65
    BASEPATH
    0.62
    createClass
    0.60
     mids
    0.60
    ngdoc
    0.58
     taro
    0.58
     estekak
    0.58
    Activations Density 0.001%

    No Known Activations