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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1157
    Prev
    Next
    INDEX
    Explanations

    the word "It" and its variations, indicating a focus on first-person or observational statements

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

    the pronoun "It" at the beginning of sentences

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

    it is

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    GEBURTSDATUM
    -0.99
    principalTable
    -0.97
     виправивши
    -0.96
    Hentet
    -0.84
    principalColumn
    -0.83
    KommentareTeilen
    -0.82
    jsonwebtoken
    -0.82
     ModelExpression
    -0.82
     Waray
    -0.82
    RetentionPolicy
    -0.82
    POSITIVE LOGITS
    zelfde
    0.69
    xious
    0.64
    ostante
    0.61
    It
    0.60
    しかし
    0.56
    kaç
    0.54
    Also
    0.52
    是一
    0.51
    cillary
    0.51
    rededor
    0.51
    Activations Density 0.072%

    No Known Activations