© 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. 28-GEMMASCOPE-RES-16K
    6. 8456
    Prev
    Next
    INDEX
    Explanations

    relationships and interactions between individuals or groups

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

    Following "be" and variations ("is", "are", "was", "were", "became")

    np_acts-logits-general · gemini-2.0-flash

    identifies roles and classifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     épaules
    -0.48
     lèvres
    -0.46
     unei
    -0.42
     a
    -0.41
     an
    -0.41
     nuits
    -0.38
    是个
    -0.37
     itself
    -0.36
     rigue
    -0.36
     oreilles
    -0.36
    POSITIVE LOGITS
     recipients
    0.95
     beneficiaries
    0.92
     successors
    0.88
     culprits
    0.85
     victims
    0.85
     proxies
    0.85
     mediators
    0.85
     toppers
    0.85
     candidates
    0.85
     subsidiaries
    0.85
    Activations Density 0.852%

    No Known Activations