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. 9971
    Prev
    Next
    INDEX
    Explanations

    collaborations between celebrities or authors in creative projects

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

    Followed by "user"

    np_acts-logits-general · gemini-2.0-flash

    company production front

    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
     térmica
    -0.30
     inmediata
    -0.30
     confirmación
    -0.28
     eccell
    -0.26
     utilidad
    -0.25
    дке
    -0.25
    handleClose
    -0.25
     lacks
    -0.24
     lady
    -0.24
     lack
    -0.24
    POSITIVE LOGITS
    OGND
    0.77
    Autoritní
    0.65
    sizeCache
    0.63
     EconPapers
    0.63
     للمعارف
    0.63
    ⤹
    0.62
    锈钢
    0.61
    adaptiveStyles
    0.60
     autobio
    0.60
     صوتيه
    0.60
    Activations Density 0.190%

    No Known Activations