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. 13736
    Prev
    Next
    INDEX
    Explanations

    expressions related to perseverance and resilience

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

    Negation or refusal

    np_acts-logits-general · gemini-2.0-flash

    excuses, complaining, laziness

    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
    GetHashCode
    -0.52
    arthed
    -0.45
    รา
    -0.44
     "}";
    -0.44
    Ớ
    -0.44
    ghest
    -0.43
     строго
    -0.43
     शु
    -0.43
    vertida
    -0.42
    严格
    -0.42
    POSITIVE LOGITS
     excuses
    0.97
     slack
    0.91
     lazy
    0.90
     wim
    0.90
     shir
    0.89
     defe
    0.88
     weak
    0.86
     laziness
    0.86
     complacency
    0.86
     coward
    0.85
    Activations Density 0.276%

    No Known Activations