© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14313
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the" in various contexts

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

    Follows "the" or possessive pronouns

    np_acts-logits-general · gemini-2.0-flash

    the followed by specific term

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    ,
    -0.43
     
    -0.41
    I
    -0.35
     in
    -0.35
    .
    -0.35
     he
    -0.34
    There
    -0.34
     short
    -0.34
     I
    -0.34
     keinem
    -0.33
    POSITIVE LOGITS
     Administrativna
    0.81
    ſſung
    0.81
     препратки
    0.74
     ویکی‌پدیا
    0.73
    <unused52>
    0.72
    <unused43>
    0.72
    <unused74>
    0.72
    <unused79>
    0.72
    <unused16>
    0.72
    <unused42>
    0.72
    Activations Density 0.432%

    No Known Activations