© 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. 3785
    Prev
    Next
    INDEX
    Explanations

    numeric and statistical data related to scientific measurements and analyses

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

    like "indicating" or "suggesting"

    np_acts-logits-general · gemini-2.0-flash

    showing or indicating results

    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
    principalColumn
    -0.60
     Wicidata
    -0.59
     StringTokenizer
    -0.58
    webElementGuid
    -0.54
    どうしても
    -0.53
    AndEndTag
    -0.53
    oa̍t
    -0.52
    HtmlAttribute
    -0.51
    ذة
    -0.51
    VersionUID
    -0.50
    POSITIVE LOGITS
     indicating
    2.27
     indicates
    2.21
     indicative
    2.13
     indicate
    2.12
     indication
    2.08
    indic
    2.07
    indicates
    1.96
     Indicates
    1.78
     INDIC
    1.78
    indicate
    1.77
    Activations Density 1.519%

    No Known Activations