© 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. 16-GEMMASCOPE-RES-16K
    11. 8342
    Prev
    Next
    INDEX
    Explanations

    statements or instructions related to returning to a previous section or text

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

    "Return to text" annotations in academic papers

    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 @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    demás
    -0.63
    anyon
    -0.60
     onPage
    -0.60
    appartamento
    -0.59
    Ứ
    -0.58
    ModelSerializer
    -0.58
    épisode
    -0.57
    episodes
    -0.57
    brica
    -0.56
    igreja
    -0.56
    POSITIVE LOGITS
     returns
    1.08
     Returns
    1.04
     Return
    1.04
     RETURN
    1.04
     return
    0.95
    Return
    0.93
    Returned
    0.93
    Returns
    0.92
    returns
    0.91
     Returned
    0.89
    Activations Density 0.115%

    No Known Activations