© 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. 14979
    Prev
    Next
    INDEX
    Explanations

    attributes related to graphical elements and their properties in diagram representations

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

    Occurrences after "max" or "minimum"

    np_acts-logits-general · gemini-2.0-flash

    maxOccurs, minOccurs, minimum height, width

    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
    脚注の使い方
    -0.92
    حوالہ
    -0.91
    __":
    -0.91
    StructEnd
    -0.88
    __":
    -0.84
    ^(@)
    -0.84
    +#+
    -0.83
     '\\;'
    -0.81
    +:+
    -0.81
     дописавши
    -0.79
    POSITIVE LOGITS
    =
    0.48
    urlopen
    0.46
     Sample
    0.46
    Sample
    0.46
    _
    0.45
    ed
    0.43
    delaire
    0.42
    =((
    0.42
    рем
    0.42
     Overall
    0.40
    Activations Density 0.050%

    No Known Activations