Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 17-GEMMASCOPE-RES-16K
    6. 6921
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word 'specific' and its variations, indicating a focus on specific details or criteria

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Patro
    -0.70
    mazoo
    -0.67
     coals
    -0.57
    ంలో
    -0.57
     serpent
    -0.56
     NLA
    -0.56
     Fielding
    -0.55
     strainer
    -0.55
    listers
    -0.55
     xenon
    -0.54
    POSITIVE LOGITS
     specific
    0.82
     Specific
    0.77
    specific
    0.75
     SPECIFIC
    0.75
    SPECIFIC
    0.73
    Specific
    0.72
     particular
    0.72
    ificity
    0.71
    BURGH
    0.69
    pecific
    0.66
    Activations Density 0.144%

    No Known Activations