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

    Neuronpedia

    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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 12803
    Prev
    Next
    INDEX
    Explanations

    instances of the word "pull" and its variations, indicating a focus on actions related to pulling or dragging

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

    the verb "pull" or "pulls" in various contexts and tenses.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Calif
    -0.37
     Storms
    -0.35
    ukunft
    -0.34
     '.';
    -0.34
    jetbrains
    -0.33
    Dots
    -0.32
    </caption>
    -0.32
     Storm
    -0.32
    Derbyniad
    -0.32
     dot
    -0.32
    POSITIVE LOGITS
     Pull
    1.46
     pull
    1.43
    Pull
    1.43
     PULL
    1.43
    pull
    1.39
     pulled
    1.34
    PULL
    1.31
    pulled
    1.29
     pulls
    1.29
     pulling
    1.27
    Activations Density 0.120%

    No Known Activations