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. 11-GEMMASCOPE-RES-16K
    6. 5295
    Prev
    Next
    INDEX
    Explanations

    phrases related to temporal and causal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -0.56
     hemsida
    -0.47
    SourceChecksum
    -0.46
     myſelf
    -0.46
     fufficient
    -0.45
     Pakai
    -0.45
    parsedMessage
    -0.45
    GOTREF
    -0.44
     Cæsar
    -0.44
    utilisons
    -0.43
    POSITIVE LOGITS
    Cyfarwyddwr
    0.43
    arau
    0.41
     '\\;'
    0.41
     المعيارى
    0.41
     Вікіпе
    0.41
     aDecoder
    0.40
    cru
    0.40
     SER
    0.39
     Bent
    0.39
    StreamWriter
    0.37
    Activations Density 1.112%

    No Known Activations