© 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. 20-GEMMASCOPE-RES-16K
    6. 8319
    Prev
    Next
    INDEX
    Explanations

    multiple expressions of seeking solutions or methods to address various challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    новниш
    -0.46
    ただの
    -0.43
     Gedanke
    -0.42
     Spisak
    -0.41
     étoit
    -0.41
    writerow
    -0.40
    ことです
    -0.38
    PreExecute
    -0.38
    InitVars
    -0.38
    +:+
    -0.37
    POSITIVE LOGITS
     ways
    0.82
     WAYS
    0.61
     Ways
    0.59
     solutions
    0.58
     τρό
    0.55
     SOLUTIONS
    0.54
    solutions
    0.52
     спосо
    0.52
    strategies
    0.52
    Ways
    0.52
    Activations Density 0.227%

    No Known Activations