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. 2927
    Prev
    Next
    INDEX
    Explanations

    topics related to economic transactions and resource distribution

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

    present time

    np_acts-logits-general · gemini-2.0-flash

    current state of affairs

    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
     للمعارف
    -0.75
    Diwedd
    -0.65
    archiviato
    -0.63
    ()?;
    -0.57
     Infórmanos
    -0.56
    Skocz
    -0.54
    flickr
    -0.52
    asantry
    -0.51
    substack
    -0.51
    ições
    -0.51
    POSITIVE LOGITS
     currently
    1.74
    currently
    1.59
     Currently
    1.49
     presently
    1.44
    Currently
    1.42
     existing
    1.31
     actuellement
    1.30
     already
    1.30
     current
    1.28
     derzeit
    1.22
    Activations Density 0.528%

    No Known Activations