© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 13668
    Prev
    Next
    INDEX
    Explanations

    phrases indicating ambiguity or criticisms related to political contexts

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

    Follows "even", "without", or similar adverbs

    np_acts-logits-general · gemini-2.0-flash

    without even a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     purpoſe
    -0.74
    XmlAccessorType
    -0.64
     ſever
    -0.63
     reaſon
    -0.62
    色々と
    -0.61
     reafon
    -0.60
    Bioaccumulative
    -0.59
     houſe
    -0.59
     neceff
    -0.59
     ſtate
    -0.59
    POSITIVE LOGITS
     even
    0.97
     slightest
    0.95
     remotely
    0.90
     iota
    0.88
     ONCE
    0.85
    even
    0.83
     ounce
    0.82
     EVEN
    0.81
     moindre
    0.80
     hint
    0.78
    Activations Density 0.207%

    No Known Activations