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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 122717
    Prev
    Next
    INDEX
    Explanations

    references to specific biological or botanical terms related to substances and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     dabei
    -0.44
     thăm
    -0.43
     getF
    -0.43
    ../../
    -0.42
    ėmis
    -0.42
    ()};
    -0.41
     Jerzy
    -0.41
    uarga
    -0.41
    CHAPTER
    -0.40
     féd
    -0.40
    POSITIVE LOGITS
     Knox
    0.80
    ano
    0.76
     Hano
    0.76
    Ano
    0.75
     Ano
    0.74
    ANO
    0.72
    Nox
    0.71
    Noo
    0.70
     No
    0.70
     Nó
    0.70
    Activations Density 0.062%

    No Known Activations