© 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. 9423
    Prev
    Next
    INDEX
    Explanations

    numeric values and weather-related terms or data

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

    after "wave" or related terms

    np_acts-logits-general · gemini-2.0-flash

    ride waves

    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
     de
    -0.46
     primary
    -0.45
     A
    -0.45
     M
    -0.44
     P
    -0.44
     All
    -0.44
     Y
    -0.43
     help
    -0.43
     av
    -0.43
     E
    -0.42
    POSITIVE LOGITS
     waves
    1.43
     wave
    1.43
     WAVE
    1.30
    wave
    1.24
     Waves
    1.24
     Wave
    1.23
    Wave
    1.20
    WAVE
    1.13
    waves
    1.12
    Waves
    1.06
    Activations Density 0.153%

    No Known Activations