© 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. 1511
    Prev
    Next
    INDEX
    Explanations

    specific terminology and concepts related to definitions and classifications

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

    ending in "ly", "ally", "bly", "tively", "ously", "ably", or "ocally"

    np_acts-logits-general · gemini-2.0-flash

    adverbs formed from stems

    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
    sterious
    -0.59
    StreetMap
    -0.54
    atalos
    -0.53
    bolista
    -0.52
    natured
    -0.52
    ageo
    -0.52
    niająca
    -0.51
    Seine
    -0.50
    epiece
    -0.47
     Christie
    -0.47
    POSITIVE LOGITS
    ally
    1.19
    antly
    1.09
    ly
    1.08
    edly
    1.08
    ingly
    1.07
    ALLY
    1.06
    tly
    1.05
    ially
    1.03
    ously
    1.01
    tely
    1.01
    Activations Density 0.317%

    No Known Activations