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. 21-GEMMASCOPE-RES-16K
    6. 502
    Prev
    Next
    INDEX
    Explanations

    references to authority, governance, and the roles of individuals or groups in a societal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     leveraging
    -0.75
     prioritizing
    -0.74
     prioritize
    -0.69
     impactful
    -0.66
     incentiv
    -0.66
     HasFactory
    -0.65
     prioritized
    -0.64
     showcasing
    -0.63
     aren
    -0.63
     targeting
    -0.61
    POSITIVE LOGITS
     doubtless
    0.66
    SourceChecksum
    0.65
    faßt
    0.65
     geheel
    0.61
    انيف
    0.60
     nevertheless
    0.58
     demikian
    0.57
     thence
    0.57
     altogether
    0.57
     således
    0.57
    Activations Density 0.688%

    No Known Activations