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-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 9464
    Prev
    Next
    INDEX
    Explanations

    references to packaging, particularly oxygen-permeable types, and their implications in medical or pharmaceutical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedCtor
    -0.84
    DockStyle
    -0.78
    OGND
    -0.75
    __":
    
    -0.74
    WithIOException
    -0.72
     linkovi
    -0.69
    MethodManager
    -0.68
    RenderAtEndOf
    -0.68
     typelib
    -0.64
    XtraBars
    -0.63
    POSITIVE LOGITS
     ventes
    0.46
     especializados
    0.44
    ysy
    0.43
    elas
    0.43
    EVT
    0.42
    ).__
    0.42
    Specialized
    0.42
    esty
    0.42
     danos
    0.42
     ponta
    0.42
    Activations Density 0.926%

    No Known Activations