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. 18-GEMMASCOPE-RES-16K
    6. 610
    Prev
    Next
    INDEX
    Explanations

    transportation-related terms and concepts

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

    Means of transportation other than cars

    np_acts-logits-general · gemini-2.0-flash

    by transportation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnknownFieldSet
    -0.47
     Leche
    -0.44
     presença
    -0.44
    oplasma
    -0.43
    issements
    -0.40
     devant
    -0.39
     čin
    -0.38
    fortawesome
    -0.38
    cellona
    -0.38
     мѣ
    -0.38
    POSITIVE LOGITS
     bicycle
    1.08
     bike
    1.06
     motorbike
    1.02
     motorcycle
    0.99
     bicycles
    0.98
     bikes
    0.94
     automobile
    0.94
    bicycle
    0.93
     overland
    0.91
    Bicycle
    0.90
    Activations Density 0.147%

    No Known Activations