© 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. 6564
    Prev
    Next
    INDEX
    Explanations

    code-related terminology and export statements

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

    the phrase "as a matter of law" and related legal conclusions about entitlement to judgment.

    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
    parsedMessage
    -0.58
     estekak
    -0.50
    帖最后由
    -0.48
     utafitiHapana
    -0.45
    الحياه
    -0.43
     مشين
    -0.43
    writeField
    -0.42
     snippetHide
    -0.42
     StatefulWidget
    -0.41
    ConstraintMaker
    -0.41
    POSITIVE LOGITS
     default
    2.34
    default
    2.13
     standard
    1.66
    Default
    1.52
     Default
    1.51
     defaulted
    1.50
    默认
    1.48
     standaard
    1.48
    デフォ
    1.45
    standard
    1.40
    Activations Density 0.374%

    No Known Activations