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. 16174
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals or references to notable figures with the name "Ed."

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

    Tokens starting with "Ed"

    np_acts-logits-general · gemini-2.0-flash

    Edward or Ed names

    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
    UrlResolution
    -0.63
     esternos
    -0.57
    Rhestr
    -0.54
    DockStyle
    -0.52
    protoimpl
    -0.51
    theoremstyle
    -0.49
    assemblée
    -0.47
    LabelTagHelper
    -0.47
    codename
    -0.46
    RenderAtEndOf
    -0.45
    POSITIVE LOGITS
     ED
    0.51
     Ed
    0.48
     ed
    0.46
    edf
    0.40
     Eddie
    0.40
     Edd
    0.39
    Ed
    0.39
     اد
    0.38
    vard
    0.38
     EDM
    0.38
    Activations Density 0.070%

    No Known Activations