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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-GEMMASCOPE-RES-16K
    6. 1521
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and their frequency in relation to individuals in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heden
    -0.50
     ervan
    -0.47
    Pratique
    -0.43
     del
    -0.40
    もので
    -0.40
    Ђ
    -0.39
     (
    -0.39
     clear
    -0.39
     suun
    -0.39
    rens
    -0.38
    POSITIVE LOGITS
     fellow
    0.89
    contentLoaded
    0.87
    AndEndTag
    0.82
    MigrationBuilder
    0.78
    EDEFAULT
    0.78
    :+:
    0.75
    interopRequire
    0.74
    phazard
    0.74
     Wicidata
    0.73
    )&&(
    0.72
    Activations Density 0.284%

    No Known Activations