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. 20-GEMMASCOPE-RES-16K
    6. 4654
    Prev
    Next
    INDEX
    Explanations

    concepts related to group dynamics and collective decision-making

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

    Follows certain keywords like "either", "where," or "that."

    np_acts-logits-general · gemini-2.0-flash

    words followed by common connectives

    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
     således
    -0.52
     Berlín
    -0.48
    PhysRevLett
    -0.48
    {'
    -0.47
     tecnici
    -0.47
     {...
    -0.46
    рий
    -0.46
     disini
    -0.45
    CPP
    -0.44
     asupra
    -0.44
    POSITIVE LOGITS
     bits
    0.93
     Bits
    0.74
     consultato
    0.72
     BoxDecoration
    0.72
    bloody
    0.72
    proper
    0.70
     bloke
    0.69
     lads
    0.69
     insuffisamment
    0.69
     Loads
    0.68
    Activations Density 0.313%

    No Known Activations