© 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. 9276
    Prev
    Next
    INDEX
    Explanations

    connecting words or phrases that indicate relationships or conjunctions

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

    "one" or "the other" appearing in text

    np_acts-logits-general · gemini-2.0-flash

    one and the other

    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
    又
    -0.44
     or
    -0.41
    단
    -0.39
     A
    -0.37
     asemenea
    -0.37
     OnTriggerEnter
    -0.37
     způ
    -0.37
    kově
    -0.36
     nochmals
    -0.36
    ื่อ
    -0.35
    POSITIVE LOGITS
    SourceChecksum
    1.04
     resourceCulture
    1.03
     CreateTagHelper
    0.99
     jScrollPane
    0.93
    setVerticalGroup
    0.91
     تضيفلها
    0.88
    Попис
    0.86
     للاسماء
    0.85
     समीक्षाओं
    0.84
    tvguidetime
    0.80
    Activations Density 0.157%

    No Known Activations