© 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. 20-GEMMASCOPE-RES-16K
    11. 11126
    Prev
    Next
    INDEX
    Explanations

    negative implications and effects related to health or biology

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

    following commas

    np_acts-logits-general · gemini-2.0-flash

    linking conjunctions and contrast

    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
     &
    -0.48
     inconvénients
    -0.41
    /.../
    -0.41
     gele
    -0.40
    them
    -0.40
    gele
    -0.40
    ()]);
    -0.39
    等
    -0.39
    Everything
    -0.38
     Anything
    -0.37
    POSITIVE LOGITS
     which
    1.45
     including
    1.37
     although
    1.23
     whereas
    1.23
    including
    1.08
    which
    1.08
     thereby
    1.08
     waarbij
    1.07
     причем
    1.07
     while
    1.06
    Activations Density 0.617%

    No Known Activations