© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 624
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and references indicating subjective experiences or personal opinions

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

    Follows "I" or "my"

    np_acts-logits-general · gemini-2.0-flash

    personal opinions and experiences

    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
     Ham
    -0.33
     dirigida
    -0.29
     
    -0.29
     ham
    -0.28
     DIFFER
    -0.27
    IGRATION
    -0.26
     llegando
    -0.25
     dasarnya
    -0.25
    ứt
    -0.25
     tud
    -0.25
    POSITIVE LOGITS
    OGND
    0.81
     المعيارى
    0.80
    DockStyle
    0.73
    GOTREF
    0.70
    StoryboardSegue
    0.68
    StringCopy
    0.66
    Наводи
    0.65
    WebVitals
    0.63
    InInspector
    0.62
    principalTable
    0.61
    Activations Density 0.929%

    No Known Activations