© 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. 7243
    Prev
    Next
    INDEX
    Explanations

    mathematical operations or calculations related to variables

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

    multiple-choice answer options in mathematical problem sets.

    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
    AutoScale
    -0.42
     CreateTagHelper
    -0.41
    ParallelGroup
    -0.39
    ImageContext
    -0.38
     corne
    -0.35
    StartTag
    -0.33
    @[+][
    -0.32
    KeyId
    -0.31
     PET
    -0.31
    BAU
    -0.31
    POSITIVE LOGITS
     b
    1.36
     B
    1.16
     getB
    1.12
    getB
    1.04
    b
    0.98
    B
    0.94
     б
    0.92
    ⓑ
    0.84
     ب
    0.81
    ⒝
    0.75
    Activations Density 0.637%

    No Known Activations