© 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. 105558
    Prev
    Next
    INDEX
    Explanations

    punctuations and specific formatting within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    
    -0.51
    ThemeOverlay
    -0.41
    OGND
    -0.40
    :+:
    -0.39
    スキ
    -0.39
    posedge
    -0.37
    发表于
    -0.36
     hjælp
    -0.35
     nuages
    -0.34
    skip
    -0.34
    POSITIVE LOGITS
    IntoConstraints
    0.68
     wireType
    0.58
    WriteTagHelper
    0.50
    StructEnd
    0.50
    MemoryWarning
    0.47
    internalType
    0.46
     iprot
    0.46
    AutoScaleMode
    0.45
     MenuView
    0.43
     carats
    0.43
    Activations Density 0.049%

    No Known Activations