© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 2986
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and their accomplishments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    proper nouns, specifically names and locations

    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
     japanese
    -0.67
     Japanese
    -0.67
    VAO
    -0.65
     япон
    -0.63
    Japanese
    -0.61
     japonais
    -0.61
     Référence
    -0.58
    日本人
    -0.54
    enumi
    -0.54
     lenker
    -0.53
    POSITIVE LOGITS
     Hank
    0.65
     Okay
    0.62
    Hank
    0.59
     Send
    0.57
    VIAF
    0.55
    setopt
    0.54
    osus
    0.52
    Okay
    0.51
    Send
    0.49
    ományos
    0.49
    Activations Density 0.204%

    No Known Activations