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. 15984
    Prev
    Next
    INDEX
    Explanations

    phrases indicating contrast or exceptions

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

    preceding "not" or "but"

    np_acts-logits-general · gemini-2.0-flash

    but not contrast

    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
    SharedCtor
    -0.49
     propOrder
    -0.48
    <?
    -0.43
    ⓧ
    -0.40
     insuffisamment
    -0.39
     mergeFrom
    -0.39
     Paglinawan
    -0.38
     ThemeData
    -0.38
    نیم
    -0.36
    PerformLayout
    -0.36
    POSITIVE LOGITS
     not
    2.69
    not
    2.02
    Not
    1.70
     Not
    1.70
     NOT
    1.63
     bukan
    1.52
    NOT
    1.50
     نه
    1.26
     nicht
    1.20
     Bukan
    1.16
    Activations Density 0.472%

    No Known Activations