© 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. 18-GEMMASCOPE-RES-16K
    11. 2837
    Prev
    Next
    INDEX
    Explanations

    complex names and scientific references

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

    Follows capitalized abbreviations or names

    np_acts-logits-general · gemini-2.0-flash

    Kirchner, Joel, knightley

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ობ
    -0.45
    ServiceException
    -0.39
     ger
    -0.39
     gé
    -0.37
     claim
    -0.36
     Oates
    -0.36
     surla
    -0.35
     مشين
    -0.35
     pack
    -0.35
     zam
    -0.34
    POSITIVE LOGITS
     InputDecoration
    0.87
    ContentLoaded
    0.86
    ValueStyle
    0.86
     Monfieur
    0.84
     myſelf
    0.83
    省市镇
    0.83
     CURIAM
    0.80
    ſelves
    0.78
     diſt
    0.77
    IntoConstraints
    0.77
    Activations Density 0.340%

    No Known Activations