© 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. 10344
    Prev
    Next
    INDEX
    Explanations

    multiple forms of legal and procedural terms related to penalties and liabilities

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

    commas and words that appear in lists or enumerations of related items.

    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
     Papa
    -0.73
     PartialEq
    -0.72
    PerPage
    -0.72
    Papa
    -0.68
    
    -0.67
    PostMapping
    -0.64
     Pope
    -0.63
     Pacific
    -0.62
    Pacific
    -0.62
    plash
    -0.61
    POSITIVE LOGITS
    AndEndTag
    0.56
     AssemblyCulture
    0.49
    SharedCtor
    0.41
     zoude
    0.40
     zucchero
    0.38
     saudara
    0.37
     silvestre
    0.37
     escalera
    0.37
     détermination
    0.36
     escaleras
    0.36
    Activations Density 1.454%

    No Known Activations