© 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-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 14977
    Prev
    Next
    INDEX
    Explanations

    references to individuals involved in actions or statements

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

    "He" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    pronoun + auxiliary verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.71
    aarrggbb
    -0.66
     resourceCulture
    -0.60
     reportedly
    -0.59
     مشارکت‌کنندگان
    -0.57
     Seem
    -0.56
    LookAnd
    -0.56
    他說
    -0.56
     बताया
    -0.56
     evidently
    -0.55
    POSITIVE LOGITS
     sengaja
    0.51
     expects
    0.51
     nadzieję
    0.45
     hoppas
    0.45
     întâ
    0.44
     personally
    0.44
    后悔
    0.43
     hopes
    0.43
     persönlich
    0.43
     feels
    0.42
    Activations Density 0.344%

    No Known Activations