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

    Neuronpedia

    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. 1-GEMMASCOPE-RES-16K
    11. 2805
    Prev
    Next
    INDEX
    Explanations

    words related to oral traditions or practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jspb
    -0.59
    UserScript
    -0.59
    帖最后由
    -0.58
    Välislingid
    -0.58
    :✨
    -0.55
     Autorizaciones
    -0.49
     createSlice
    -0.49
    SourceChecksum
    -0.47
     незавершена
    -0.46
    httphttps
    -0.46
    POSITIVE LOGITS
    fo
    1.22
     Fo
    1.20
    Fo
    1.19
     Fools
    1.16
     fo
    1.14
     fool
    1.12
     Fool
    1.09
    Fool
    1.03
    fool
    1.02
     fools
    1.01
    Activations Density 0.257%

    No Known Activations