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. 21-GEMMASCOPE-RES-16K
    6. 2070
    Prev
    Next
    INDEX
    Explanations

    terms related to vehicles, specifically motors and motor types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebVitals
    -0.62
     aikaa
    -0.60
    XmlEnum
    -0.55
    Wider
    -0.54
    WSGI
    -0.51
    MergeFrom
    -0.51
    pēc
    -0.50
    thold
    -0.50
    dır
    -0.50
    اشة
    -0.50
    POSITIVE LOGITS
    sports
    0.68
    home
    0.68
    homes
    0.62
     neuron
    0.59
    ized
    0.59
     Motor
    0.58
     MOTOR
    0.57
     vehicles
    0.56
     jsPsych
    0.56
    olla
    0.55
    Activations Density 0.072%

    No Known Activations