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. 20-GEMMASCOPE-RES-16K
    6. 121
    Prev
    Next
    INDEX
    Explanations

    timely expressions indicating the present or ongoing situations

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

    the word "Now" at the start of a sentence

    np_acts-logits-general · gemini-2.0-flash

    Now, followed by discourse or explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    今でも
    -0.67
     now
    -0.62
     professionali
    -0.62
    scalatest
    -0.62
    vari
    -0.60
    enciaga
    -0.59
    TestBed
    -0.59
    middels
    -0.59
     giapp
    -0.58
     ContentValues
    -0.57
    POSITIVE LOGITS
    adays
    0.92
    HERE
    0.78
    heres
    0.76
    ValueStyle
    0.74
    GEBURTSDATUM
    0.72
    ww
    0.70
    wwww
    0.70
    wwwwwwww
    0.66
    værende
    0.65
    here
    0.65
    Activations Density 0.071%

    No Known Activations