© 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
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 101707
    Prev
    Next
    INDEX
    Explanations

    key terms related to mental health disorders and symptoms

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

    Function words or connective phrases appearing at clause boundaries that establish logical, temporal, or structural relationships between parts of text.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    isNameExpr
    -0.40
    lad
    -0.36
     Arn
    -0.36
    '
    -0.35
     Guille
    -0.34
    �
    -0.34
     Or
    -0.34
     din
    -0.34
     Kü
    -0.34
     
    -0.33
    POSITIVE LOGITS
     esternos
    0.90
    Personendaten
    0.84
    GOTREF
    0.84
     propOrder
    0.83
     EconPapers
    0.82
    UnusedPrivate
    0.79
    EDEFAULT
    0.79
     surla
    0.79
    parsedMessage
    0.79
    writeFieldEnd
    0.74
    Activations Density 0.237%

    No Known Activations