© 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. 2938
    Prev
    Next
    INDEX
    Explanations

    various HTML and XML tags and entities

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

    HTML angle brackets, greater than or less than

    np_acts-logits-general · gemini-2.0-flash

    html, code, and symbols

    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
    setTime
    -0.50
    (!__
    -0.47
     "
    -0.46
    ண
    -0.45
     petto
    -0.44
    ("./
    -0.44
     ↑
    -0.43
    пли
    -0.43
     _
    -0.43
     bety
    -0.43
    POSITIVE LOGITS
     Efq
    0.97
     resourceCulture
    0.74
     الاطلاع
    0.73
    脚注の使い方
    0.72
     myſelf
    0.71
    felves
    0.69
     defStyleAttr
    0.69
     مشين
    0.68
    ]--;
    0.68
    ագրություններ
    0.68
    Activations Density 0.212%

    No Known Activations