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. 4-GEMMASCOPE-RES-16K
    6. 15651
    Prev
    Next
    INDEX
    Explanations

    occurrences of the phrase "of" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -0.96
     ―――――
    -0.89
     purpoſe
    -0.83
     légère
    -0.82
    
    -0.81
     Majefty
    -0.79
     ainfi
    -0.77
     itſelf
    -0.76
    orithm
    -0.75
     ſind
    -0.75
    POSITIVE LOGITS
    OutOf
    1.30
     outta
    1.24
     out
    0.85
     Out
    0.82
     into
    0.78
     aus
    0.72
    OUT
    0.72
     INTO
    0.70
     OUT
    0.70
     fuori
    0.69
    Activations Density 0.068%

    No Known Activations