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. 20-GEMMASCOPE-RES-16K
    6. 9582
    Prev
    Next
    INDEX
    Explanations

    phrases or concepts related to ideals and perfectionism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ANDUM
    -0.69
    adpleegd
    -0.65
    новниш
    -0.64
    DataMember
    -0.63
     שוליים
    -0.62
     Roskov
    -0.61
    ThroughAttribute
    -0.59
    OGND
    -0.59
     nahilalakip
    -0.57
    AndEndTag
    -0.57
    POSITIVE LOGITS
     perfect
    2.60
     ideal
    2.48
    perfect
    2.46
    ideal
    2.30
    Perfect
    2.21
     Perfect
    2.20
    Ideal
    2.17
     perfection
    2.15
     Ideal
    2.12
     PERFECT
    2.09
    Activations Density 0.292%

    No Known Activations