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-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 74840
    Prev
    Next
    INDEX
    Explanations

    instances of the words "the," "he," and phonetic variations of "that."

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

    the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    OGND
    -0.88
    SharedDtor
    -0.79
     мәкал
    -0.69
     يتيمه
    -0.68
    GEBURTSDATUM
    -0.68
    ChildScrollView
    -0.67
     للاسماء
    -0.66
    RenderAtEndOf
    -0.66
    Tikang
    -0.66
    elemField
    -0.66
    POSITIVE LOGITS
     the
    1.09
    The
    0.87
    the
    0.81
     The
    0.81
     THE
    0.75
    THE
    0.59
     their
    0.58
     tbe
    0.56
     its
    0.55
    sthe
    0.55
    Activations Density 0.012%

    No Known Activations