Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 11196
    Prev
    Next
    INDEX
    Explanations

    terms related to licenses and certifications in professional fields

    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
    ReusableCell
    -0.82
    ConstraintMaker
    -0.79
    featureID
    -0.77
    +#+#
    -0.76
     <=",
    -0.75
     snippetHide
    -0.75
    InsertCommand
    -0.68
    InitVars
    -0.63
    ttino
    -0.62
     وتسجيلات
    -0.62
    POSITIVE LOGITS
     legally
    0.76
     regulated
    0.66
     legal
    0.62
     licensed
    0.62
     license
    0.61
     regulations
    0.60
     certified
    0.60
     lawfully
    0.59
     laws
    0.58
     registered
    0.56
    Activations Density 0.592%

    No Known Activations