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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11488
    Prev
    Next
    INDEX
    Explanations

    references to governmental assistance and funding initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
    styleable
    -0.46
    Билгалдахарш
    -0.45
     itſelf
    -0.44
    glades
    -0.43
    SBATCH
    -0.43
    AISSEE
    -0.43
    艋
    -0.42
     nhiêu
    -0.42
     invokingState
    -0.42
     onCancelled
    -0.42
    POSITIVE LOGITS
    consulting
    0.60
     consulting
    0.58
     advising
    0.58
     Consulting
    0.57
     assistance
    0.57
    Consulting
    0.56
     assisting
    0.54
    assistance
    0.54
     ADVICE
    0.54
     consultants
    0.54
    Activations Density 0.282%

    No Known Activations