© 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. 17-GEMMASCOPE-RES-16K
    6. 13092
    Prev
    Next
    INDEX
    Explanations

    postpositions or particles that indicate the object or action of a sentence

    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
    theless
    -0.98
     Chwiliwch
    -0.79
    expandindo
    -0.74
     itſelf
    -0.73
     Efq
    -0.67
     ་་
    -0.66
     Jefus
    -0.63
    ValueStyle
    -0.62
     Eud
    -0.62
     recti
    -0.61
    POSITIVE LOGITS
    ALLOWED
    0.62
     me
    0.57
     оригіналу
    0.57
     assigned
    0.55
     Tom
    0.54
    ()}>
    0.52
     Think
    0.52
    ))/(
    0.52
     U
    0.52
    ugget
    0.52
    Activations Density 0.037%

    No Known Activations