Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 1879
    Prev
    Next
    INDEX
    Explanations

    code syntax elements and structures, particularly focusing on functions and conditionals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     println
    -0.64
     printf
    -0.55
     print
    -0.55
     LOGGER
    -0.53
     elif
    -0.52
     QString
    -0.51
     cout
    -0.50
     public
    -0.50
     theſe
    -0.50
     def
    -0.49
    POSITIVE LOGITS
     poveznice
    0.47
     Wolken
    0.46
    if
    0.46
    limiento
    0.46
    ectady
    0.45
    ajevo
    0.44
     Ignorance
    0.44
     Ärz
    0.43
     pavements
    0.43
     Gästen
    0.42
    Activations Density 0.362%

    No Known Activations