© 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-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 5582
    Prev
    Next
    INDEX
    Explanations

    phrases connected to immunological reactions and protein interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TextInputType
    -0.65
    SourceChecksum
    -0.61
    intellij
    -0.60
     betweenstory
    -0.59
    Tikang
    -0.58
     فريبيس
    -0.57
     linkovi
    -0.55
     Wallflower
    -0.54
    migrationBuilder
    -0.53
     wireType
    -0.53
    POSITIVE LOGITS
     proteins
    0.66
     peptides
    0.66
     polypep
    0.64
     purified
    0.64
     protein
    0.63
     recombinant
    0.62
    album
    0.60
    etu
    0.59
     tetanus
    0.58
     polypeptide
    0.57
    Activations Density 3.115%

    No Known Activations