© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 4227
    Prev
    Next
    INDEX
    Explanations

    references to micro-level concepts or factors in a variety of contexts

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

    Following the word "micro"

    np_acts-logits-general · gemini-2.0-flash

    micro prefix and its common continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enderror
    -0.56
    >`;
    -0.55
    $.}
    -0.52
    daß
    -0.50
    }{*}{}
    -0.49
    vatar
    -0.49
    )\}
    -0.49
    ))^{
    -0.49
    **)
    -0.48
    คาร
    -0.48
    POSITIVE LOGITS
    Micro
    0.85
     Micro
    0.82
     micro
    0.81
     MICRO
    0.78
     微
    0.73
     Mic
    0.72
    micro
    0.70
     micros
    0.69
     Mikro
    0.68
    微
    0.67
    Activations Density 0.139%

    No Known Activations