© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 16066
    Prev
    Next
    INDEX
    Explanations

    structural elements of programming code such as braces and parentheses

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

    `return` keyword or similar function returns

    np_acts-logits-general · gemini-2.0-flash

    return after certain sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -0.61
    <bos>
    -0.57
    elemField
    -0.56
     الرياضيه
    -0.55
     continuant
    -0.54
    roffen
    -0.53
    cokinetics
    -0.53
     đẩy
    -0.52
    OGND
    -0.51
    ]--;
    -0.51
    POSITIVE LOGITS
     return
    3.24
    return
    3.23
     returning
    2.61
     Return
    2.59
     returned
    2.54
     returns
    2.44
     Returning
    2.41
     RETURN
    2.40
    Returning
    2.22
    Return
    2.18
    Activations Density 0.203%

    No Known Activations