© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 28330
    Prev
    Next
    INDEX
    Explanations

    references to modular components or systems

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

    software module definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •List

    No Comments

    Negative Logits
     Goodrich
    -0.46
    TheReal
    -0.45
     najleps
    -0.44
    <b>
    -0.43
    Getty
    -0.42
    best
    -0.40
    </b>
    -0.40
     Navidad
    -0.40
    fast
    -0.39
    s
    -0.39
    POSITIVE LOGITS
     Module
    1.38
     module
    1.30
    Module
    1.25
     Modules
    1.24
    module
    1.18
     MODULE
    1.17
     NgModule
    1.16
     modules
    1.14
    MODULE
    1.11
    odule
    1.05
    Activations Density 0.019%

    No Known Activations