© 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. 4951
    Prev
    Next
    INDEX
    Explanations

    terms that express changes or transitions over time

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

    temporal expressions with words like "yet," "anymore," "again," and other time-related indicators.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    temporal expressions indicating past or incomplete states (words like "anymore," "yet," "again," "now").

    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
    InputBorder
    -0.62
    ']))
    
    -0.56
    ")));
    
    -0.56
    AddHtmlAttribute
    -0.54
     AssemblyCompany
    -0.53
    PreferredItem
    -0.53
    ()))
    
    -0.53
    "))
    
    -0.52
    TintMode
    -0.52
    }")
    
    -0.51
    POSITIVE LOGITS
     since
    0.44
     CallOverrides
    0.41
     during
    0.40
     geweest
    0.40
     unless
    0.38
    adays
    0.38
    !
    0.38
    følgelig
    0.37
    etera
    0.36
     when
    0.36
    Activations Density 0.533%

    No Known Activations