© 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 - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 4290
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and operations

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

    mathematical expressions and numerical operations (particularly multiplication, equations, and digit sequences).

    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
     enfans
    -0.69
    ंदीखरीदारी
    -0.59
    twimg
    -0.55
     avoit
    -0.50
     propOrder
    -0.49
     avoient
    -0.48
     känna
    -0.46
     ögon
    -0.45
    vänt
    -0.43
     bär
    -0.42
    POSITIVE LOGITS
     estekak
    0.50
     Vikipedi
    0.40
     $:$
    0.39
     PUL
    0.39
    metra
    0.38
     gren
    0.37
     tron
    0.36
    :''
    0.36
    aliens
    0.36
     Bacter
    0.36
    Activations Density 0.088%

    No Known Activations