© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 7181
    Prev
    Next
    INDEX
    Explanations

    variables and concepts related to derivatives and mathematical functions

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

    mathematical notation and derivative operations in technical/scientific text.

    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
    تقاوى
    -0.63
    GIVEREF
    -0.57
     дописавши
    -0.57
     JpaRepository
    -0.56
     CreateTagHelper
    -0.54
    Autoritní
    -0.54
    Rüyada
    -0.53
    存于互联网档案馆
    -0.51
    帖最后由
    -0.51
    MigrationBuilder
    -0.50
    POSITIVE LOGITS
     evaluation
    1.16
     evaluations
    1.15
     evaluated
    1.14
     evaluate
    1.08
     Evaluations
    1.04
     Evaluate
    0.99
     Evaluation
    0.98
     evalu
    0.98
     evaluates
    0.97
     évalu
    0.97
    Activations Density 1.784%

    No Known Activations