© 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. 123
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the concept of existence or being

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

    "be" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    be followed by a descriptor

    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
     inol
    -0.58
    SW
    -0.49
     inaugurated
    -0.48
     pede
    -0.47
    sans
    -0.47
     raided
    -0.46
    ＆
    -0.46
    {{--
    -0.45
     pedig
    -0.44
    igu
    -0.44
    POSITIVE LOGITS
     AssemblyCulture
    1.04
    IntoConstraints
    0.76
     itſelf
    0.75
     الحره
    0.74
     propOrder
    0.70
     HasFactory
    0.69
     varandra
    0.69
     reaſon
    0.66
     Anſ
    0.66
     архивлан
    0.65
    Activations Density 1.481%

    No Known Activations