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. 18-GEMMASCOPE-RES-16K
    6. 791
    Prev
    Next
    INDEX
    Explanations

    technical jargon related to maintenance and servicing

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

    Regular or scheduled actions

    np_acts-logits-general · gemini-2.0-flash

    periodic maintenance and screening

    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
    abestanden
    -0.56
    ंदीखरीदारी
    -0.55
    sertation
    -0.53
    awtextra
    -0.49
    disambiguation
    -0.49
    DropColumn
    -0.49
    reactstrap
    -0.48
    libert
    -0.48
    ętr
    -0.47
    GEBURTSDATUM
    -0.47
    POSITIVE LOGITS
     periodic
    1.50
     periodically
    1.44
     Periodic
    1.42
     yearly
    1.42
    Periodic
    1.42
     regularly
    1.40
     Regularly
    1.32
     annual
    1.32
     annually
    1.31
    定期
    1.28
    Activations Density 0.344%

    No Known Activations