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
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 5614
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific letters and symbols in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TRAIN
    -0.40
     hereto
    -0.38
    пыт
    -0.37
    собенности
    -0.36
    écriture
    -0.36
    GeneratedMessage
    -0.35
    ⓧ
    -0.35
    РТ
    -0.35
    писание
    -0.35
    ценка
    -0.35
    POSITIVE LOGITS
    DockStyle
    0.57
     שוליים
    0.56
    +#+#
    0.56
    wing
    0.56
     дописавши
    0.49
    фициальный
    0.47
    ViewInit
    0.47
    ceans
    0.44
    ficial
    0.44
    собенно
    0.44
    Activations Density 0.271%

    No Known Activations