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. 16336
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to expectations and predictions

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

    "expected" and variants

    np_acts-logits-general · gemini-2.0-flash

    what is expected

    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
    bindParam
    -0.67
    providedIn
    -0.64
    gdx
    -0.62
    zepte
    -0.57
    userManager
    -0.57
     насељу
    -0.54
    openConnection
    -0.54
     Chua
    -0.52
    medes
    -0.52
     canciones
    -0.51
    POSITIVE LOGITS
    antly
    0.94
     Expect
    0.84
     betweenstory
    0.81
     EXPECT
    0.80
     تضيفلها
    0.78
     Expectations
    0.73
    ancy
    0.72
    wiſe
    0.70
    expect
    0.70
    uality
    0.69
    Activations Density 0.088%

    No Known Activations