© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2039
    Prev
    Next
    INDEX
    Explanations

    statements and quotes made by individuals, particularly those conveying information or feelings

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

    reporting or quoting phrases like "he said" or "she added".

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    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
     betweenstory
    -0.84
    webElementXpaths
    -0.71
     للمعارف
    -0.69
     noDo
    -0.65
    transQ
    -0.65
    reportWebVitals
    -0.62
     againſt
    -0.61
     Houſe
    -0.60
     OFDb
    -0.60
     itſelf
    -0.60
    POSITIVE LOGITS
     added
    0.46
     señaló
    0.42
     añadió
    0.41
     statement
    0.41
     explicó
    0.38
     agregó
    0.38
     asimismo
    0.37
     añade
    0.37
     mencionó
    0.36
     Asimismo
    0.36
    Activations Density 0.045%

    No Known Activations