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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 29943
    Prev
    Next
    INDEX
    Explanations

    occurrences of the abbreviation "U.S." in the context of legal documents

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

    U.S. abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    ulongan
    -0.78
    XmlType
    -0.69
     limão
    -0.68
    ementara
    -0.65
    ſammen
    -0.64
     própri
    -0.64
    客様
    -0.59
    attutto
    -0.59
    səhifə
    -0.58
    ðsíða
    -0.58
    POSITIVE LOGITS
    iacute
    0.49
    ntilde
    0.47
    oacute
    0.45
    auml
    0.44
    <bos>
    0.42
    aacute
    0.41
    S
    0.40
    uuml
    0.40
    œil
    0.40
    i
    0.40
    Activations Density 0.037%

    No Known Activations