© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 111349
    Prev
    Next
    INDEX
    Explanations

    references to immune cell activity and related processes

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

    hemocytes and aquaculture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ölkerung
    -0.40
     AssemblyCulture
    -0.38
     transfieras
    -0.37
     souff
    -0.35
    lifetime
    -0.35
    StatusBadRequest
    -0.34
    TabLayout
    -0.34
    ђа
    -0.34
     Mutter
    -0.34
    stateMutability
    -0.33
    POSITIVE LOGITS
     shrimp
    0.64
     Shrimp
    0.62
    Shrimp
    0.59
     Aquaculture
    0.59
     shrimps
    0.58
     aquaculture
    0.57
     invertebrate
    0.55
     prawns
    0.52
     prawn
    0.52
    vertebrate
    0.51
    Activations Density 0.318%

    No Known Activations