© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 12617
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the passage of time and significant events over the years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     שוליים
    -0.52
    grü
    -0.45
    gridy
    -0.42
    Bakgrunnsstoff
    -0.41
    wapV
    -0.40
    Források
    -0.38
    ện
    -0.38
    NTIS
    -0.38
    MENAFN
    -0.36
    Referencies
    -0.36
    POSITIVE LOGITS
     ujednoznacz
    0.43
    UnusedPrivate
    0.42
    AsUp
    0.40
    จัง
    0.39
    productive
    0.39
    setArguments
    0.39
     terang
    0.38
     fill
    0.37
     moments
    0.37
     przesz
    0.37
    Activations Density 0.618%

    No Known Activations