© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11856
    Prev
    Next
    INDEX
    Explanations

    Repeated instances of the word "the"

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

    function words marking definite reference, especially the definite article introducing noun phrases.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the word "the" when it precedes technical or specialized nouns in formal/scientific contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     
    -0.46
    ,
    -0.43
    This
    -0.36
     short
    -0.36
     in
    -0.36
    y
    -0.35
     Mad
    -0.35
    ’
    -0.35
     for
    -0.34
     he
    -0.33
    POSITIVE LOGITS
    ſſung
    0.78
     ویکی‌پدیا
    0.77
    ]")]
    0.71
    <unused42>
    0.68
    <unused23>
    0.68
    <unused3>
    0.68
    <unused43>
    0.68
    <unused52>
    0.68
    <unused74>
    0.68
    [@BOS@]
    0.68
    Activations Density 0.526%

    No Known Activations