© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 12741
    Prev
    Next
    INDEX
    Explanations

    punctuation marks indicating emotional or emphatic expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.96
     समीक्षाओं
    -0.88
     дописавши
    -0.82
     مشين
    -0.81
    awtextra
    -0.79
     OFDb
    -0.79
     Roskov
    -0.78
    makeConstraints
    -0.76
    ValueStyle
    -0.73
     estekak
    -0.71
    POSITIVE LOGITS
     Famous
    0.47
    观的
    0.45
     Sequel
    0.44
     jod
    0.44
     Clarion
    0.43
    OfType
    0.42
     lattices
    0.41
     conduction
    0.41
    polite
    0.41
     electrically
    0.41
    Activations Density 0.405%

    No Known Activations