© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8939
    Prev
    Next
    INDEX
    Explanations

    references to customized elements or products

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

    technical API documentation and code definitions for "Custom Element Registry".

    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
    HasAnnotation
    -0.46
     saites
    -0.45
    Autoritní
    -0.41
     Tatsache
    -0.41
    下载附件
    -0.39
    Przeczytaj
    -0.38
     jadx
    -0.37
    lysninger
    -0.37
     igenom
    -0.36
     naturalistic
    -0.36
    POSITIVE LOGITS
    isable
    0.85
    izability
    0.68
    izable
    0.65
    isasi
    0.65
    arily
    0.64
    isation
    0.64
    isations
    0.63
    setCustom
    0.63
    ised
    0.60
     Custom
    0.59
    Activations Density 0.052%

    No Known Activations