© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 8450
    Prev
    Next
    INDEX
    Explanations

    words related to negation and affirmation in a comparative context

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

    "Only", "even", followed by a conditional word

    np_acts-logits-general · gemini-2.0-flash

    only if and even though

    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
    NameInMap
    -0.79
     houſe
    -0.71
     Monfieur
    -0.69
     ſmall
    -0.69
     Majefty
    -0.66
     purpoſe
    -0.65
     Efq
    -0.65
    ();)
    -0.63
    fromnode
    -0.63
     iſt
    -0.61
    POSITIVE LOGITS
     because
    0.74
     by
    0.74
     insofar
    0.67
     at
    0.66
     in
    0.63
     from
    0.61
     during
    0.61
     through
    0.61
     while
    0.60
     henvisninger
    0.57
    Activations Density 0.221%

    No Known Activations