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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 11259
    Prev
    Next
    INDEX
    Explanations

    elements related to comedy and comedians

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

    "[number] nm" (nanometers)

    np_acts-logits-general · gemini-2.0-flash

    laser nm wavelength

    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
    namon
    -0.60
    Parse
    -0.51
    ByExample
    -0.51
    heem
    -0.51
    prefixer
    -0.51
     Roskov
    -0.50
     oto
    -0.49
     Margot
    -0.49
    イレ
    -0.49
    awtextra
    -0.48
    POSITIVE LOGITS
     comedian
    0.88
     Comedy
    0.88
     comedians
    0.86
     comedy
    0.84
    Comedy
    0.83
    comedy
    0.83
     stand
    0.65
    ьаж
    0.65
    OGND
    0.65
    stand
    0.63
    Activations Density 0.170%

    No Known Activations