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. 9-GEMMASCOPE-RES-16K
    6. 6578
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and web development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyProduct
    -0.49
    ifndef
    -0.40
    UnitTesting
    -0.38
    InternalFrame
    -0.38
    ArrowToggle
    -0.36
    atisk
    -0.35
    Parameteri
    -0.35
     Reichen
    -0.34
     незавершена
    -0.34
     hefyd
    -0.34
    POSITIVE LOGITS
    Drupal
    0.69
     Drupal
    0.61
    rupal
    0.55
     Nashville
    0.54
    Nashville
    0.53
     Austin
    0.52
    modelBuilder
    0.52
    Edinburgh
    0.52
    Austin
    0.51
     Edinburgh
    0.50
    Activations Density 0.426%

    No Known Activations