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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 107870
    Prev
    Next
    INDEX
    Explanations

    repeated mentions of "you" to focus on the reader's perspective and engagement

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

    actions regarding you

    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
    <bos>
    -0.79
    pośred
    -0.54
     BoxFit
    -0.40
    Aktualisiert
    -0.40
     alcuna
    -0.39
    KindOfClass
    -0.39
     other
    -0.38
     outras
    -0.38
     boîtier
    -0.38
     ladite
    -0.38
    POSITIVE LOGITS
    You
    1.20
    you
    1.18
     you
    1.16
    YOU
    1.05
     YOU
    1.02
     You
    0.98
    Você
    0.94
     você
    0.83
    Mereka
    0.82
    你
    0.81
    Activations Density 0.155%

    No Known Activations