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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 1706
    Prev
    Next
    INDEX
    Explanations

    indicators of potential medical warnings or important safety information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.59
    μβρίου
    -0.58
    readValue
    -0.57
    consulté
    -0.57
     CanadaChoose
    -0.57
     referrerpolicy
    -0.56
     المعرف
    -0.56
    एको
    -0.56
     mole
    -0.55
    السكان
    -0.55
    POSITIVE LOGITS
    зулта
    0.62
    WriteLiteral
    0.58
     newBuilder
    0.56
     págs
    0.56
    soever
    0.54
     referenties
    0.54
     Parton
    0.53
    jasper
    0.53
     Retard
    0.52
    (""));
    0.52
    Activations Density 0.186%

    No Known Activations