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. 4819
    Prev
    Next
    INDEX
    Explanations

    instances of the word "hang" and its variations, indicating a focus on forms of hanging or suspending

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

    "hanging" or "hang"

    np_acts-logits-general · gemini-2.0-flash

    hang out

    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
     Gesch
    -0.52
    省市镇
    -0.48
    parency
    -0.48
     colline
    -0.48
     insuffisamment
    -0.47
    Contributor
    -0.46
     TestBed
    -0.46
    cisme
    -0.45
    REFERRED
    -0.45
    ymce
    -0.45
    POSITIVE LOGITS
     Hang
    1.39
     hang
    1.35
     HANG
    1.34
     hung
    1.24
     hanging
    1.22
     hangs
    1.20
     Hanging
    1.18
    Hanging
    1.17
    Hang
    1.16
    hanging
    1.10
    Activations Density 0.057%

    No Known Activations