© 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. 8809
    Prev
    Next
    INDEX
    Explanations

    quotes and references related to identity and obligations

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

    Text following "I AM", quotation marks, or certain pronouns

    np_acts-logits-general · gemini-2.0-flash

    "I AM" statements

    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
    enderror
    -0.50
    djangoproject
    -0.50
    enetrable
    -0.47
    ourable
    -0.45
    UnknownFieldSet
    -0.44
     snippetHide
    -0.43
     Chwiliwch
    -0.42
    utives
    -0.42
     τῆς
    -0.41
    Tembelea
    -0.40
    POSITIVE LOGITS
     betweenstory
    0.47
     دریافت‌شده
    0.45
     Absch
    0.42
    Sofa
    0.40
    todo
    0.40
    ®
    0.40
    ®.
    0.39
    Wednesday
    0.38
     Wikiseite
    0.38
     okuyayım
    0.38
    Activations Density 0.838%

    No Known Activations