© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 12592
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions or requests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     constantemente
    -0.63
     constantly
    -0.63
     zufolge
    -0.59
     înal
    -0.57
     sorella
    -0.57
     always
    -0.57
     nyky
    -0.56
     nowadays
    -0.56
    kegaard
    -0.56
     regularly
    -0.56
    POSITIVE LOGITS
    VersionUID
    0.73
    proved
    0.68
    σουμε
    0.65
    脚注の使い方
    0.62
    ført
    0.59
     Bioaccumulative
    0.59
    われた
    0.58
     cracked
    0.57
    :+:
    0.57
    FailureListener
    0.57
    Activations Density 0.032%

    No Known Activations