© 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. 9-GEMMASCOPE-RES-16K
    11. 11205
    Prev
    Next
    INDEX
    Explanations

    closing parentheses and brackets in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     houſe
    -0.47
     pleaſure
    -0.44
     ſche
    -0.43
    ſelf
    -0.40
    ſelves
    -0.39
    ställning
    -0.36
     Eſ
    -0.35
     Houſe
    -0.35
     tox
    -0.34
    heatmap
    -0.34
    POSITIVE LOGITS
     *)
    0.88
    enterOuterAlt
    0.78
     *>(
    0.77
    ########.
    0.69
     *)&
    0.68
     *)__
    0.67
    __*/
    0.66
    rungsseite
    0.64
     **)
    0.63
    posedge
    0.62
    Activations Density 0.090%

    No Known Activations