© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 4303
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Hol" along with its variations and capitalizations

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

    followed by "enstein", "sten", "sh", "mgren" or "na"

    np_acts-logits-general · gemini-2.0-flash

    names starting with Hol

    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
     CreateTagHelper
    -0.77
    parsedMessage
    -0.63
    usercontent
    -0.61
    queryInterface
    -0.61
     Roskov
    -0.60
     ostavi
    -0.60
    __":
    -0.60
    principalColumn
    -0.58
    ArrowToggle
    -0.57
    Jeografia
    -0.56
    POSITIVE LOGITS
    oplasts
    0.52
    stdout
    0.51
    tură
    0.51
     الفلك
    0.47
    ródło
    0.46
    rungsseite
    0.46
    mbol
    0.46
    rlpool
    0.45
    laston
    0.45
    mogorov
    0.45
    Activations Density 0.093%

    No Known Activations