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

    Neuronpedia

    Jacobian LensNEW
    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. 10778
    Prev
    Next
    INDEX
    Explanations

    expressions of high intensity or strong emphasis

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

    Following "highly" plus an adjective

    np_acts-logits-general · gemini-2.0-flash

    highly plus descriptor

    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
    ArgsConstructor
    -0.75
     wholly
    -0.63
     entirely
    -0.62
     great
    -0.61
    MemoryWarning
    -0.60
     very
    -0.60
     constamment
    -0.59
     completely
    -0.59
    danno
    -0.59
     aveug
    -0.56
    POSITIVE LOGITS
     nakalista
    0.59
    Попис
    0.58
     debated
    0.58
     ddelweddau
    0.57
     overrated
    0.57
     Signalez
    0.55
     anticipated
    0.55
    Likely
    0.54
    IntoConstraints
    0.53
     outnumbered
    0.52
    Activations Density 0.120%

    No Known Activations