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. 24-GEMMASCOPE-RES-16K
    6. 2408
    Prev
    Next
    INDEX
    Explanations

    information related to transportation services and infrastructure

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

    Follows prepositions ("as", "at", "in")

    np_acts-logits-general · gemini-2.0-flash

    places and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Saran
    -0.60
     Ukrain
    -0.56
    IActionResult
    -0.56
     /\.(
    -0.54
    ControllerAdvice
    -0.53
     Monaghan
    -0.53
     Taipei
    -0.51
     /\.
    -0.51
    ->__
    -0.49
     Kamin
    -0.46
    POSITIVE LOGITS
     Swindon
    0.69
     مشين
    0.66
     Bournemouth
    0.66
    ]--;
    0.62
     Christchurch
    0.60
     Wiltshire
    0.60
     Dorchester
    0.59
     Southampton
    0.59
    Odkazy
    0.59
    Southampton
    0.58
    Activations Density 0.125%

    No Known Activations