Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 7856
    Prev
    Next
    INDEX
    Explanations

    negations and their variations in sentences

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

    negative contractions, particularly phrases that use "isn't," "doesn't," or similar forms.

    oai_token-act-pair · gpt-4oTriggered by @christianthto

    Apostrophes after contractions of "to do"

    np_acts-logits-general · gemini-2.0-flash

    negative contractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    -0.78
     Signalez
    -0.68
     Савезне
    -0.67
     "..\..\..\
    -0.67
    исленность
    -0.67
    ]--;
    -0.66
    曖昧さ回避
    -0.66
    niająca
    -0.61
     Biôgrafia
    -0.61
     cherchés
    -0.61
    POSITIVE LOGITS
    '
    1.18
    ’
    1.11
    ´
    0.83
    `
    0.82
    ''
    0.76
    &#
    0.69
    ʼ
    0.69
    '[
    0.67
    ʻ
    0.66
    ‟
    0.66
    Activations Density 0.106%

    No Known Activations