© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 64293
    Prev
    Next
    INDEX
    Explanations

    situations involving moments of reflection and interpersonal connections

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

    balcony or window

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ={({
    -0.50
    Tren
    -0.49
     Waray
    -0.47
     surla
    -0.46
     houſe
    -0.46
    cooper
    -0.45
     noDo
    -0.45
    Prefer
    -0.45
    OGND
    -0.45
     SCAN
    -0.44
    POSITIVE LOGITS
     balcony
    1.38
     window
    1.35
     balcón
    1.23
     balconies
    1.20
     Window
    1.16
     fenêtre
    1.13
     Balcony
    1.13
    window
    1.11
     finestra
    1.10
     Balkon
    1.10
    Activations Density 0.018%

    No Known Activations