© 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. 4586
    Prev
    Next
    INDEX
    Explanations

    references to common programming practices or issues in coding

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

    conversational explanations and justifications in technical Q&A responses.

    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
    NameInMap
    -0.50
    CloseOperation
    -0.47
    теристика
    -0.47
     &___
    -0.46
    exitRule
    -0.44
    SBATCH
    -0.44
     poffe
    -0.44
    PDO
    -0.40
    HtmlAttribute
    -0.40
    nbt
    -0.40
    POSITIVE LOGITS
     debugging
    0.70
     implementations
    0.67
     usability
    0.65
     workflows
    0.63
     Entwick
    0.62
    ใช้งาน
    0.59
     funcionalidades
    0.57
     developer
    0.56
     refactor
    0.55
     developers
    0.55
    Activations Density 2.457%

    No Known Activations