Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3135
    Prev
    Next
    INDEX
    Explanations

    elements related to programming and data structures in code snippets

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

    Often followed by punctuation or unrelated tokens

    np_acts-logits-general · gemini-2.0-flash

    programming variables and values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     []);
    -0.63
     []),
    -0.60
    ())));
    -0.60
    ."),
    -0.58
     {}));
    -0.58
    )));
    -0.57
    ())),
    -0.56
    ()],
    -0.55
    =$?
    -0.55
    }`);
    -0.54
    POSITIVE LOGITS
    Geplaatst
    0.81
    Rüyada
    0.78
    yntaxException
    0.78
     оригіналу
    0.76
    ValueStyle
    0.76
     odkazy
    0.74
     كومونز
    0.74
    modelBuilder
    0.73
    TargetException
    0.73
    agisse
    0.73
    Activations Density 0.194%

    No Known Activations