© 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. 20-GEMMASCOPE-RES-16K
    6. 5928
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "medium" in various contexts

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

    the word "medium" or statistical analysis related to medium-sized categories.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    The neuron activates for the word "medium" when it's used to describe size, scale, or degree.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     atque
    -0.54
     Irán
    -0.54
     enfans
    -0.53
     pleaſure
    -0.52
     règne
    -0.51
     ſen
    -0.51
     armée
    -0.50
     êtres
    -0.50
    peace
    -0.50
     noires
    -0.50
    POSITIVE LOGITS
    inum
    0.75
    IUM
    0.72
    arium
    0.69
    lium
    0.69
     Nimbus
    0.68
    um
    0.67
    idium
    0.67
    ium
    0.67
    idum
    0.66
    uum
    0.66
    Activations Density 0.260%

    No Known Activations