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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15737
    Prev
    Next
    INDEX
    Explanations

    references to specific cellular mechanisms and their roles in biological processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    цездатний
    -0.58
     GenerationType
    -0.56
    :✨
    -0.53
     queſta
    -0.52
    acquisto
    -0.52
    yntaxException
    -0.52
     réguli
    -0.50
    
    -0.50
     régulière
    -0.50
     gacha
    -0.50
    POSITIVE LOGITS
     mechanism
    0.58
     mechanisms
    0.56
     action
    0.45
     interaction
    0.44
     influence
    0.42
    mechanism
    0.41
     effect
    0.40
     processes
    0.40
     <<<<<<<<<<<<<<
    0.40
     interplay
    0.40
    Activations Density 1.417%

    No Known Activations