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. 7873
    Prev
    Next
    INDEX
    Explanations

    instances of the word "just" and related phrases indicating time or quantity

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

    "just" followed by time/distance

    np_acts-logits-general · gemini-2.0-flash

    just before a measure or direction

    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
     almeno
    -0.75
    AddTagHelper
    -0.74
     jopa
    -0.71
    directly
    -0.69
    ControllerAdvice
    -0.69
     atleast
    -0.68
     للمعارف
    -0.68
     متعلقه
    -0.67
    至少
    -0.66
     justru
    -0.65
    POSITIVE LOGITS
     flick
    0.55
     weeks
    0.54
     steps
    0.54
    CGRectMake
    0.53
     handful
    0.52
     fraction
    0.52
     footsteps
    0.52
     shy
    0.49
     clicks
    0.49
     numberOfRows
    0.49
    Activations Density 0.132%

    No Known Activations