© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 12015
    Prev
    Next
    INDEX
    Explanations

    terms related to botany and biology, specifically pertaining to plant and food references

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    before "pyloridis" or "philid"

    np_acts-logits-general · gemini-2.0-flash

    Campylobacter pyloridis, snake names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Luar
    -0.56
     Moscú
    -0.55
     defaultstate
    -0.55
     Jerusalén
    -0.54
     Holanda
    -0.53
     Nowy
    -0.52
     Praze
    -0.52
     París
    -0.51
     Suiza
    -0.51
     flach
    -0.50
    POSITIVE LOGITS
    wapV
    0.68
    Abit
    0.53
     EconPapers
    0.52
    dafx
    0.51
    ThemeOverlay
    0.49
    xnn
    0.49
    躇
    0.47
    Scri
    0.45
    [];
    0.45
    ⤹
    0.44
    Activations Density 0.751%

    No Known Activations