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-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5095
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics

    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
    getA
    -0.52
     RequestMethod
    -0.50
     bodyParser
    -0.49
    ſo
    -0.48
     profitably
    -0.46
    endsection
    -0.46
     AGENT
    -0.46
    você
    -0.46
     GPL
    -0.46
    vereignty
    -0.45
    POSITIVE LOGITS
    UNRELATED
    0.61
    tagHelperRunner
    0.57
    SBATCH
    0.54
    ruptedException
    0.49
     onItemClick
    0.49
    umán
    0.49
    InjectMocks
    0.47
    Twelve
    0.46
    édrale
    0.46
     Twelve
    0.45
    Activations Density 0.493%

    No Known Activations