© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 11786
    Prev
    Next
    INDEX
    Explanations

    statements involving returning or coming back from a situation or an event

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

    words related to returning or coming back.

    oai_token-act-pair · gpt-4oTriggered by @christianthto

    Preceding the word "return"

    np_acts-logits-general · gemini-2.0-flash

    return to text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.74
    WriteAttribute
    -0.70
    DockStyle
    -0.68
     AssemblyTitle
    -0.65
    EDEFAULT
    -0.64
    IsContent
    -0.60
     snippetHide
    -0.58
    DebuggerNonUser
    -0.58
     MainAxisSize
    -0.57
    posedge
    -0.56
    POSITIVE LOGITS
     return
    4.22
     Return
    3.64
     returned
    3.63
     returning
    3.59
     returns
    3.52
    return
    3.48
     RETURN
    3.35
    Return
    3.33
     Returning
    3.24
    Returning
    3.06
    Activations Density 0.988%

    No Known Activations