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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 9105
    Prev
    Next
    INDEX
    Explanations

    details related to physical conditions and measurements in a scientific context

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

    before "transition", "limit", or "level"

    np_acts-logits-general · gemini-2.0-flash

    at the limit or transition

    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
     ouder
    -0.41
    lunch
    -0.38
    rawDesc
    -0.37
    Breed
    -0.36
     AppComponent
    -0.36
     psiqui
    -0.36
     jongen
    -0.35
     Menschheit
    -0.35
    Ger
    -0.35
     namorado
    -0.35
    POSITIVE LOGITS
     Biôgrafia
    0.54
     ویکی‌پدی
    0.52
    лтамалар
    0.49
     borderline
    0.49
    Portail
    0.48
    ギリ
    0.47
    transQ
    0.46
     Roskov
    0.45
     GenerationType
    0.45
    ぎり
    0.45
    Activations Density 0.569%

    No Known Activations