© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 1914
    Prev
    Next
    INDEX
    Explanations

    function calls and return statements in code

    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
     demanded
    -0.90
     Demands
    -0.89
    Requested
    -0.81
     begged
    -0.80
     Asking
    -0.80
     Asked
    -0.79
     Requested
    -0.79
    Asking
    -0.79
     demands
    -0.76
     asks
    -0.75
    POSITIVE LOGITS
     request
    1.23
    request
    1.15
    OGND
    0.68
     للاسماء
    0.52
     reu
    0.49
     مشين
    0.44
     کیلوم
    0.42
     за
    0.41
     regu
    0.40
    fortawesome
    0.40
    Activations Density 0.447%

    No Known Activations