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. 3021
    Prev
    Next
    INDEX
    Explanations

    references to legal rights and procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    References to laws, rules, statutes, regulations, and formal legal citations (including acronyms and numbered rule/section citations).

    oai_token-act-pair · gpt-5-miniTriggered by @phamvanluong2003
    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
    ImageContext
    -0.54
    Chosen
    -0.49
     Chosen
    -0.46
    bo
    -0.44
    mande
    -0.41
     an
    -0.41
    setcounter
    -0.40
    -
    -0.39
    SharedCtor
    -0.39
     până
    -0.38
    POSITIVE LOGITS
    iastes
    0.96
    othesis
    0.84
     للمعارف
    0.82
    LookAnd
    0.80
    PhysRevD
    0.80
    bootstrapcdn
    0.79
    odils
    0.75
     Мексичка
    0.72
    ﷺ
    0.72
    urtstag
    0.71
    Activations Density 0.933%

    No Known Activations