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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 14322
    Prev
    Next
    INDEX
    Explanations

    references to specific proteins and their characteristics in biological contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    types and members

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    WithFormat
    -0.35
    Logical
    -0.33
     Avg
    -0.32
     gif
    -0.32
     air
    -0.32
     bags
    -0.31
     liqu
    -0.31
     avg
    -0.31
     trus
    -0.31
     bag
    -0.30
    POSITIVE LOGITS
    CppMethod
    0.67
     ujednoznacz
    0.61
     tampaknya
    0.60
    UrlResolution
    0.59
    Personensuche
    0.59
    ReusableCell
    0.59
     InputDecoration
    0.59
     parecen
    0.58
    msgTypes
    0.58
    ParallelGroup
    0.57
    Activations Density 0.284%

    No Known Activations