© 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. 20-GEMMASCOPE-RES-16K
    6. 11875
    Prev
    Next
    INDEX
    Explanations

    specific plant species and related biological terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     plegable
    -0.35
     lipat
    -0.34
     Secretario
    -0.31
     rueda
    -0.31
     amigas
    -0.31
     Italij
    -0.31
     cooperación
    -0.30
     amico
    -0.30
     razones
    -0.29
     organes
    -0.29
    POSITIVE LOGITS
    :✨
    0.84
    ModelAdmin
    0.82
     pinulongan
    0.77
    EDEFAULT
    0.76
    Rohy
    0.73
    IUrlHelper
    0.72
    mybatisplus
    0.71
    intios
    0.71
     EconPapers
    0.70
     autorytatywna
    0.68
    Activations Density 0.885%

    No Known Activations