© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 4336
    Prev
    Next
    INDEX
    Explanations

    references to authority figures and religious themes

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

    Punctuation after specific words

    np_acts-logits-general · gemini-2.0-flash

    specific questions and statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.63
    出版年
    -0.51
    <thead>
    -0.50
    Bakgrunnsstoff
    -0.50
     nahilalakip
    -0.48
    ViewFeatures
    -0.48
     fince
    -0.47
     leaſt
    -0.46
     lesz
    -0.45
    intéress
    -0.45
    POSITIVE LOGITS
    LookAnd
    0.41
     propOrder
    0.41
     betweenstory
    0.41
    StylePriority
    0.40
     lived
    0.37
     did
    0.36
     hikay
    0.35
     was
    0.32
    MigrationBuilder
    0.32
     story
    0.31
    Activations Density 0.142%

    No Known Activations