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. 25-GEMMASCOPE-RES-16K
    6. 6046
    Prev
    Next
    INDEX
    Explanations

    instances of measuring electoral outcomes and processes related to political votes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __':
    
    -0.57
    __":
    -0.54
    __':
    -0.53
    ADELPHIA
    -0.53
     Marquette
    -0.53
    emang
    -0.53
     Walkover
    -0.53
    extAlignment
    -0.52
     useEffect
    -0.51
     ISNI
    -0.51
    POSITIVE LOGITS
     strong
    0.81
    strong
    0.74
     Strong
    0.72
     acids
    0.69
    Strong
    0.68
     acid
    0.68
     sterke
    0.67
     STRONG
    0.67
     concentrated
    0.66
    STRONG
    0.65
    Activations Density 0.748%

    No Known Activations