© 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. 16-GEMMASCOPE-RES-16K
    11. 11618
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence of specific references or citations

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

    Tokens preceding ordinal numbers

    np_acts-logits-general · gemini-2.0-flash

    phrases starting with "in the" or "in this"

    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
     \%$.
    -0.66
     חיצוניים
    -0.66
     فريبيس
    -0.65
    .");
    -0.65
    ;");
    -0.65
    .);
    -0.63
    ([]);
    -0.60
    .";
    -0.60
    *;
    -0.59
    Спасылкі
    -0.59
    POSITIVE LOGITS
     entanto
    0.65
     AssemblyCulture
    0.62
    AndEndTag
    0.61
     obstante
    0.59
     inoltre
    0.57
    djangoproject
    0.57
     case
    0.51
     inilah
    0.49
    Additionally
    0.47
     moreover
    0.47
    Activations Density 0.713%

    No Known Activations