© 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 EvalsExportsAPI 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. 10781
    Prev
    Next
    INDEX
    Explanations

    significant themes and transformations in storytelling or narrative development

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

    take on, take root, take off, stick

    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
    tagHelperRunner
    -0.42
     ddelweddau
    -0.39
    WebServlet
    -0.36
    AutoScaleMode
    -0.36
     EdgeInsets
    -0.36
     tege
    -0.35
    Vanjske
    -0.35
    IRQn
    -0.35
    webElement
    -0.34
     CGPoint
    -0.34
    POSITIVE LOGITS
     stick
    1.26
     sticking
    1.19
     Stick
    1.16
    Stick
    1.14
     sticks
    1.13
    stick
    1.11
     STICK
    1.05
    sticks
    0.97
     Sticks
    0.97
    STICK
    0.95
    Activations Density 0.094%

    No Known Activations