© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 7581
    Prev
    Next
    INDEX
    Explanations

    keywords related to return statements in programming code

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

    Code containing "return" statements

    np_acts-logits-general · gemini-2.0-flash

    return statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GenerationType
    -0.80
    ConstraintMaker
    -0.63
    StoryboardSegue
    -0.61
     beginnetje
    -0.58
     '{@
    -0.58
    》.
    -0.58
    ?».
    -0.56
    Portail
    -0.56
     mapStateToProps
    -0.56
    BufferException
    -0.55
    POSITIVE LOGITS
     false
    0.71
     true
    0.58
     False
    0.54
     early
    0.53
    false
    0.53
     Void
    0.52
     FALSE
    0.52
     Himo
    0.52
    Void
    0.51
     Unit
    0.51
    Activations Density 0.048%

    No Known Activations