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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 7895
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and reactions involving water, ammonium, and various metal ions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bel
    -0.57
    rungsseite
    -0.56
    ere
    -0.54
    sty
    -0.53
    sti
    -0.53
    dish
    -0.53
    hed
    -0.52
    焦
    -0.51
    Архівовано
    -0.51
     disco
    -0.51
    POSITIVE LOGITS
     water
    0.91
     vatten
    0.90
    httphttps
    0.90
     água
    0.83
     Water
    0.83
     Вода
    0.81
    onViewCreated
    0.81
     WATER
    0.81
     woda
    0.80
    Water
    0.79
    Activations Density 0.305%

    No Known Activations