© 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. 12562
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "from," indicating references to sources or origins

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

    import statements with quoted file paths or module names.

    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
    PreferredItem
    -0.47
    StartTag
    -0.44
    ༘
    -0.43
     ModelExpression
    -0.41
     lenker
    -0.40
     acho
    -0.38
    RTSC
    -0.38
     totalidad
    -0.35
     pember
    -0.35
     doigt
    -0.35
    POSITIVE LOGITS
     "./
    0.66
     './
    0.65
     nahilalakip
    0.63
     "../
    0.63
     '../
    0.59
    "./
    0.47
    期刊论文
    0.47
     uVar
    0.47
     ./
    0.46
    './
    0.46
    Activations Density 0.035%

    No Known Activations