© 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. 8121
    Prev
    Next
    INDEX
    Explanations

    numerical data and references related to highways and routes

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

    Interstate highway and route numbers

    np_acts-logits-general · gemini-2.0-flash

    CYP and numbers

    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
    tagHelperRunner
    -1.00
    ConstraintMaker
    -0.91
    awtextra
    -0.90
    帖最后由
    -0.86
    SourceChecksum
    -0.86
    AndEndTag
    -0.80
    دانشنامهٔ
    -0.79
    الحياه
    -0.78
    ⓧ
    -0.76
    endphp
    -0.76
    POSITIVE LOGITS
     
    0.49
    SerializedName
    0.45
    2
    0.44
    1
    0.43
    3
    0.41
    4
    0.40
    gæ
    0.38
    economia
    0.37
    ség
    0.37
     szív
    0.35
    Activations Density 0.615%

    No Known Activations