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. 3-GEMMASCOPE-RES-16K
    6. 11986
    Prev
    Next
    INDEX
    Explanations

    the word "of" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Houſe
    -0.76
     Efq
    -0.75
    rancy
    -0.72
     ſtate
    -0.71
    libft
    -0.70
     houſe
    -0.68
    !("{
    -0.67
     løpet
    -0.65
     Eſ
    -0.65
    ofür
    -0.63
    POSITIVE LOGITS
     several
    1.26
    several
    1.21
    Several
    1.16
     Several
    1.15
     many
    1.12
     numerous
    1.08
    Numerous
    1.04
     Plusieurs
    1.02
    many
    1.00
    MANY
    1.00
    Activations Density 0.107%

    No Known Activations