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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 7944
    Prev
    Next
    INDEX
    Explanations

    numerical specifications and performance characteristics of vehicles

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

    Numbers followed by "cylinder" or "speed"

    np_acts-logits-general · gemini-2.0-flash

    engine transmission cylinder count

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -0.67
    InitVars
    -0.64
    complexContent
    -0.62
    Παραπομπές
    -0.56
     tanggung
    -0.54
    enumi
    -0.49
    itudine
    -0.48
    fscanf
    -0.47
     @"/
    -0.47
    ❹
    -0.47
    POSITIVE LOGITS
     door
    0.69
    cylinder
    0.68
    door
    0.65
     cylinder
    0.65
     DOOR
    0.64
    cyl
    0.64
     Cyl
    0.64
     cyl
    0.62
     Door
    0.62
     speed
    0.60
    Activations Density 0.144%

    No Known Activations