© 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. 7-GEMMASCOPE-RES-16K
    11. 15103
    Prev
    Next
    INDEX
    Explanations

    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 @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſch
    -0.75
     $_(
    -0.69
     houſe
    -0.65
     ſche
    -0.64
    ulemon
    -0.61
     quæ
    -0.59
    ſelf
    -0.57
     ſever
    -0.56
    ſelves
    -0.55
     bookId
    -0.55
    POSITIVE LOGITS
    return
    2.58
     return
    1.73
     Return
    1.28
    Return
    1.14
     returns
    1.12
     RETURN
    1.11
     returned
    1.07
    returns
    1.02
     returning
    1.02
    RETURN
    1.00
    Activations Density 0.062%

    No Known Activations