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. 20-GEMMASCOPE-RES-16K
    6. 7311
    Prev
    Next
    INDEX
    Explanations

    terms related to regulations and restrictions on weapons and violence

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

    Statements of permissibility, prohibition, or allowance after "this," "are," "is," etc

    np_acts-logits-general · gemini-2.0-flash

    legality and permission

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anskje
    -0.60
    OrNil
    -0.59
     completeness
    -0.56
     kidnapped
    -0.56
    UpInside
    -0.55
    UVEN
    -0.55
     inertia
    -0.54
    Indep
    -0.54
    writeField
    -0.53
    PropertyChanged
    -0.52
    POSITIVE LOGITS
     allowed
    2.03
     permitted
    2.02
     permissible
    1.82
     Allowed
    1.78
    allowed
    1.78
    permitted
    1.67
    Allowed
    1.65
     allowable
    1.65
     forbidden
    1.60
     prohibited
    1.58
    Activations Density 0.545%

    No Known Activations