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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1456
    Prev
    Next
    INDEX
    Explanations

    terms and variations related to the concept of "lo" and its various representations

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

    "Lo" and similar capitalization at the beginning of words

    np_acts-logits-general · gemini-2.0-flash

    words starting with Lo

    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
    HtmlAttribute
    -0.75
    帖最后由
    -0.66
     Eſ
    -0.66
    AnchorStyles
    -0.64
     Monfieur
    -0.64
     BoxFit
    -0.59
    Становништво
    -0.59
     PLAINTIFF
    -0.59
    ########.
    -0.59
     purpoſe
    -0.59
    POSITIVE LOGITS
     Lo
    0.58
     LO
    0.57
    Lo
    0.51
    !("{
    0.50
    arithmic
    0.49
    mallows
    0.48
    InstrumentedTest
    0.47
     Loeb
    0.47
     lobes
    0.45
    posedge
    0.45
    Activations Density 0.095%

    No Known Activations