Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 16-GEMMASCOPE-RES-16K
    6. 12702
    Prev
    Next
    INDEX
    Explanations

    temporal references or dates

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

    Numbers within dates and times

    np_acts-logits-general · gemini-2.0-flash

    dates and unique identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    تقاوى
    -0.79
    andExpect
    -0.77
    enumii
    -0.75
     tartalomajánló
    -0.72
     Мексичка
    -0.70
    RTLI
    -0.70
    참고
    -0.69
     beginnetje
    -0.69
     mergeFrom
    -0.69
     ISNI
    -0.69
    POSITIVE LOGITS
    ↵↵
    0.63
    <eos>
    0.51
    UVWXYZ
    0.48
     betweenstory
    0.46
     Ucraina
    0.45
     года
    0.43
    literals
    0.41
    。
    0.40
    ال
    0.40
     luft
    0.39
    Activations Density 0.135%

    No Known Activations