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
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 10042
    Prev
    Next
    INDEX
    Explanations

    instances of speech or quotations

    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
     nonUne
    -0.56
     CanadaChoose
    -0.47
     propOrder
    -0.47
     ujednoznacz
    -0.46
    Personendaten
    -0.45
    كويكب
    -0.45
     getIs
    -0.44
    rungsseite
    -0.43
     EconPapers
    -0.43
     peindre
    -0.42
    POSITIVE LOGITS
    MessageTagHelper
    0.53
    enderror
    0.44
    tagHelperRunner
    0.42
     betweenstory
    0.41
    transQ
    0.40
     STC
    0.39
    writeFieldEnd
    0.39
    gypti
    0.39
    Jîn
    0.39
    IGraphics
    0.39
    Activations Density 0.081%

    No Known Activations