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. 12-GEMMASCOPE-RES-16K
    6. 5172
    Prev
    Next
    INDEX
    Explanations

    expressions of hope or positive anticipation regarding outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     basically
    -0.51
     essentially
    -0.50
    bes
    -0.50
    almost
    -0.49
    basically
    -0.46
    essentially
    -0.44
    よう
    -0.43
     MUST
    -0.43
     almost
    -0.42
     fabri
    -0.42
    POSITIVE LOGITS
    jalá
    0.93
    ValueStyle
    0.89
     ffilmiau
    0.86
    rawDesc
    0.82
    GIVEREF
    0.80
    abestanden
    0.78
    🤞
    0.76
    
    0.74
     بتوان
    0.74
    PerformLayout
    0.72
    Activations Density 0.199%

    No Known Activations