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. 9-GEMMASCOPE-RES-16K
    6. 9292
    Prev
    Next
    INDEX
    Explanations

    words related to intensity and severity

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

    The neuron detects phrases discussing the intensity of something, particularly in scientific and medical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abetes
    -0.56
    thâu
    -0.54
    tvguidetime
    -0.52
     Италијани
    -0.52
    béco
    -0.52
     Democrá
    -0.51
    ├──
    -0.50
    Portale
    -0.49
    gsSP
    -0.49
    MemoryWarning
    -0.49
    POSITIVE LOGITS
     intensity
    2.00
     intense
    1.90
     Intensity
    1.88
    Intensity
    1.73
    intensity
    1.73
    intense
    1.64
     Intense
    1.62
     intensities
    1.62
     intens
    1.60
     Intens
    1.59
    Activations Density 0.354%

    No Known Activations