Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 795
    Prev
    Next
    INDEX
    Explanations

    terminologies related to biological classification and characteristics of viruses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.94
     оригіналу
    -0.75
    Revenir
    -0.69
    arraycopy
    -0.60
    HtmlAttribute
    -0.60
    FileVersion
    -0.57
    MemoryWarning
    -0.57
    matchCondition
    -0.57
    ViewFeatures
    -0.56
    MigrationBuilder
    -0.55
    POSITIVE LOGITS
     family
    1.40
    family
    1.23
     Family
    1.17
    Family
    1.16
     FAMILY
    1.11
     genus
    1.09
     familia
    0.98
    FAMILY
    0.97
     families
    0.97
     famille
    0.96
    Activations Density 0.523%

    No Known Activations