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. 24-GEMMASCOPE-RES-16K
    6. 8263
    Prev
    Next
    INDEX
    Explanations

    words related to knowledge and understanding

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

    Followed by "know" or a synonym

    np_acts-logits-general · gemini-2.0-flash

    knowing something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kháu
    -0.76
    显得
    -0.49
    üman
    -0.48
     Ideas
    -0.47
    zkod
    -0.46
     Erwä
    -0.46
    tagHelperRunner
    -0.45
    newtheorem
    -0.45
    instead
    -0.45
     istället
    -0.44
    POSITIVE LOGITS
     intimately
    1.03
     firsthand
    0.85
     Bescheid
    0.82
     well
    0.81
     better
    0.78
     intuitively
    0.75
     جيد
    0.72
    enough
    0.70
     enough
    0.69
    Personendaten
    0.69
    Activations Density 0.242%

    No Known Activations