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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 14-GEMMASCOPE-RES-16K
    6. 10686
    Prev
    Next
    INDEX
    Explanations

    references to residential or real estate properties and their characteristics

    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
    featureID
    -0.61
     utafitiHapana
    -0.59
    HttpFoundation
    -0.58
    Eloquent
    -0.55
     dép
    -0.52
    ExecuteReader
    -0.52
    tréal
    -0.51
    extAlignment
    -0.51
    ITURE
    -0.51
    ForRow
    -0.50
    POSITIVE LOGITS
     neighbourhood
    0.72
     neighborhood
    0.71
     subdivision
    0.67
    subdivision
    0.64
    fontName
    0.61
    Residential
    0.61
     насељу
    0.61
     neighbourhoods
    0.59
    neighborhood
    0.59
     residential
    0.58
    Activations Density 0.071%

    No Known Activations