© 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. 1855
    Prev
    Next
    INDEX
    Explanations

    code-related keywords and package or import statements in programming languages

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

    programming-related keywords like 'import', 'package', and file extensions like '.php', '.cpp', and '.h'.

    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
     
    -0.50
    ↵↵
    -0.40
    #
    -0.40
    ↵
    -0.40
    <strong>
    -0.38
     with
    -0.38
    -
    -0.37
    ,
    -0.37
      
    -0.37
     or
    -0.36
    POSITIVE LOGITS
     autorytatywna
    1.41
     незавершена
    1.33
     estekak
    1.31
     ब्रेकडाउन
    1.29
    RegressionTest
    1.28
    TypedDataSet
    1.27
     surla
    1.24
    
    1.24
    IUrlHelper
    1.23
     snippetHide
    1.23
    Activations Density 0.054%

    No Known Activations