© 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. 20-GEMMASCOPE-RES-16K
    11. 6195
    Prev
    Next
    INDEX
    Explanations

    expressions related to dreams and aspirations

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

    preceding or related to "dream(s)"

    np_acts-logits-general · gemini-2.0-flash

    dream or dreams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    laje
    -0.47
    textAlign
    -0.45
     Manners
    -0.45
    IVer
    -0.44
     procede
    -0.44
    latimes
    -0.44
    ichtlich
    -0.43
     faci
    -0.43
    わざ
    -0.43
     proced
    -0.43
    POSITIVE LOGITS
     dream
    2.89
     dreams
    2.82
    dream
    2.42
    dreams
    2.31
     dreamed
    2.27
     dreaming
    2.25
     DREAM
    2.25
     Dream
    2.17
     Dreams
    2.17
     rêve
    2.16
    Activations Density 0.198%

    No Known Activations