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. 16236
    Prev
    Next
    INDEX
    Explanations

    instances of criticism and legal consequences

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

    Preceding words of "for"

    np_acts-logits-general · gemini-2.0-flash

    for or because

    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
    WithIOException
    -0.56
    transQ
    -0.54
    providedIn
    -0.53
    IndentedString
    -0.51
     ExecuteAsync
    -0.50
     ब्रेकडाउन
    -0.50
    <?
    -0.50
    DockStyle
    -0.48
    fromnode
    -0.48
    AnchorStyles
    -0.47
    POSITIVE LOGITS
     for
    1.20
     wegen
    0.70
     dafür
    0.68
     because
    0.65
     kerana
    0.65
     dėl
    0.60
     zaradi
    0.59
    สำหรับ
    0.57
     για
    0.57
    for
    0.57
    Activations Density 0.370%

    No Known Activations