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. 5-GEMMASCOPE-RES-16K
    6. 14497
    Prev
    Next
    INDEX
    Explanations

    words that emphasize certainty and clarity

    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
    inam
    -0.67
    er
    -0.66
     courants
    -0.63
    ER
    -0.62
     Baer
    -0.62
     solares
    -0.62
    DateField
    -0.62
     μά
    -0.60
    AndEndTag
    -0.60
     heart
    -0.59
    POSITIVE LOGITS
    clearly
    1.43
     obviously
    1.36
    obviously
    1.36
     clearly
    1.32
     Clearly
    1.30
    Clearly
    1.27
    Obviously
    1.24
     Obviously
    1.23
     nahilalakip
    0.92
     obviamente
    0.91
    Activations Density 0.056%

    No Known Activations