© 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. 66506
    Prev
    Next
    INDEX
    Explanations

    significant changes or transformations in relationships and situations

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

    state changes

    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
    Not in Any Lists

    No Comments

    Negative Logits
     vermeiden
    -0.39
    mbggenerated
    -0.35
     {!
    -0.34
     volgen
    -0.34
     toller
    -0.33
     hoort
    -0.32
     étoient
    -0.32
     voelen
    -0.32
    (!_
    -0.31
    alami
    -0.31
    POSITIVE LOGITS
    BeginContext
    0.65
    AccessorTable
    0.54
    ieteur
    0.50
    rawDesc
    0.47
    ButterKnife
    0.46
    IntoConstraints
    0.46
    わけです
    0.46
    yczą
    0.46
     createSprite
    0.45
    出版年
    0.45
    Activations Density 0.069%

    No Known Activations