© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 11512
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts related to polynomials and their properties

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

    mathematical notation and symbolic expressions with subscripts and superscripts.

    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
     getFirst
    -0.47
    ]--;
    -0.47
     Geiſt
    -0.46
     ddelwed
    -0.45
    ftance
    -0.45
     GOtt
    -0.45
    Parcelize
    -0.44
    OCCURRED
    -0.42
    ſchaft
    -0.42
    JsonInclude
    -0.42
    POSITIVE LOGITS
    第
    0.50
    Itoa
    0.47
     i
    0.46
    DockStyle
    0.46
     iload
    0.44
     ith
    0.43
     Corresponding
    0.40
    enumi
    0.40
     nth
    0.40
     endfor
    0.40
    Activations Density 1.415%

    No Known Activations