© 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. 9-GEMMASCOPE-RES-16K
    11. 12516
    Prev
    Next
    INDEX
    Explanations

    phrases related to the usage or application of items or methods

    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
    #+#
    -0.43
    äum
    -0.40
    beke
    -0.38
    gro
    -0.38
     invitamos
    -0.38
    Autoritní
    -0.37
    ⓧ
    -0.37
    queo
    -0.37
     ank
    -0.37
    CWE
    -0.37
    POSITIVE LOGITS
     used
    0.97
     use
    0.95
     Used
    0.91
     Use
    0.88
    Used
    0.85
     Usage
    0.85
     usage
    0.85
     사용
    0.82
     تستخدم
    0.79
     uses
    0.78
    Activations Density 0.567%

    No Known Activations