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. 20-GEMMASCOPE-RES-16K
    6. 12740
    Prev
    Next
    INDEX
    Explanations

    sentences discussing probability and statistics

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

    Calculating likelihood, chances, probability or odds

    np_acts-logits-general · gemini-2.0-flash

    likelihood and probability

    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
     GenerationType
    -0.84
     оригіналу
    -0.54
     joindre
    -0.49
    اعمال
    -0.49
    GenerationType
    -0.49
     Wikimedijinoj
    -0.47
     imageNamed
    -0.46
    セラー
    -0.46
    feri
    -0.46
    ValueGenerated
    -0.45
    POSITIVE LOGITS
     probability
    2.71
     likelihood
    2.65
     chances
    2.40
    probability
    2.34
     likely
    2.29
     probabilities
    2.22
     Probability
    2.21
     odds
    2.20
     probab
    2.15
     Likelihood
    2.15
    Activations Density 0.735%

    No Known Activations