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

    Neuronpedia

    Jacobian LensNEW
    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. 15737
    Prev
    Next
    INDEX
    Explanations

    elements related to software or technical discussions

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

    Tokens before the beginning of an alternative option

    np_acts-logits-general · gemini-2.0-flash

    also, or, otherwise, anyway

    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
    ArrowToggle
    -0.92
     referenties
    -0.83
    LookAnd
    -0.81
    GEBURTSDATUM
    -0.80
     disponibilités
    -0.77
    InjectAttribute
    -0.77
    '])){
    -0.75
    Dabei
    -0.74
     gyhoeddwyd
    -0.73
     <<<<<<<<<<<<<<
    -0.72
    POSITIVE LOGITS
    Also
    0.84
     Also
    0.83
     Otherwise
    0.81
     also
    0.76
     Anyway
    0.71
     otherwise
    0.70
    Anyway
    0.70
    Otherwise
    0.67
    also
    0.66
     ALSO
    0.64
    Activations Density 0.254%

    No Known Activations