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-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15404
    Prev
    Next
    INDEX
    Explanations

    words related to taking or making actions

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

    Follows "take," "make," or "buy."

    np_acts-logits-general · gemini-2.0-flash

    take or make

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CodeAttribute
    -0.49
    enumi
    -0.36
    Brien
    -0.35
    @[+][
    -0.35
     [*]
    -0.34
     sod
    -0.34
    行き
    -0.33
     purpoſe
    -0.33
    umented
    -0.33
    Rujuakan
    -0.32
    POSITIVE LOGITS
    verwijspagina
    0.65
    rungsseite
    0.63
    setVerticalGroup
    0.60
     يتيمه
    0.57
     ujednoznacz
    0.56
    VPWR
    0.52
     betweenstory
    0.51
     surla
    0.50
     wikipagina
    0.50
     Walkover
    0.50
    Activations Density 0.325%

    No Known Activations