© 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. 22-GEMMASCOPE-RES-16K
    11. 7623
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to polymers and their properties

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

    Curing, crosslinking, or drying

    np_acts-logits-general · gemini-2.0-flash

    curing processes and limitations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.61
     '\\;'
    -0.56
    AccessorTable
    -0.56
     Administrativna
    -0.55
    Кру
    -0.49
     peritoneal
    -0.49
    cdon
    -0.49
     Ceinture
    -0.48
     shaved
    -0.48
     Rounded
    -0.48
    POSITIVE LOGITS
     cure
    0.87
     curing
    0.81
     cured
    0.79
    cure
    0.74
     Cure
    0.74
    cured
    0.74
    Cure
    0.73
     cures
    0.64
    ldorf
    0.60
    ocyan
    0.59
    Activations Density 0.544%

    No Known Activations