© 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. 16-GEMMASCOPE-RES-16K
    11. 1259
    Prev
    Next
    INDEX
    Explanations

    technical terms and elements related to data processing or programming

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

    figures or tables

    np_acts-logits-general · gemini-2.0-flash

    table, list, and diagram references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ']))
    -0.50
     Himo
    -0.47
     unknownFields
    -0.47
    lius
    -0.47
    INCT
    -0.47
    長的
    -0.46
    EMAN
    -0.46
    cjon
    -0.46
    WriteTagHelper
    -0.45
     lệ
    -0.45
    POSITIVE LOGITS
    abestanden
    0.80
    IUrlHelper
    0.78
    ValueStyle
    0.66
     المعيارى
    0.63
    FontOfSize
    0.56
     greateſt
    0.55
    の中の
    0.54
    中略
    0.54
    umpad
    0.53
    antaranya
    0.53
    Activations Density 1.142%

    No Known Activations