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. 16272
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be" in various tenses and contexts

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

    Follows "that are" or "that is"

    np_acts-logits-general · gemini-2.0-flash

    are descriptions of existing states

    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
     onCreateView
    -0.36
     என்ப
    -0.32
    hiasan
    -0.32
    I
    -0.32
    という
    -0.30
    这是一
    -0.30
     тех
    -0.30
     the
    -0.30
    จึง
    -0.30
     G
    -0.30
    POSITIVE LOGITS
     MainAxisSize
    0.88
     Normdatei
    0.75
    Vidite
    0.73
    Chham
    0.73
    ArgsConstructor
    0.72
    extAlignment
    0.71
    AsUp
    0.70
    RectangleBorder
    0.67
    <pad>
    0.66
    <unused3>
    0.66
    Activations Density 0.267%

    No Known Activations