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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 3581
    Prev
    Next
    INDEX
    Explanations

    specific words related to music and musical elements

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

    ending in "et," "ets," or "eting."

    np_acts-logits-general · gemini-2.0-flash

    ending in ets or eting

    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
    Portale
    -0.60
    Datuak
    -0.53
    enumi
    -0.49
    sopp
    -0.48
    spartner
    -0.46
    deur
    -0.46
     endfor
    -0.45
    usión
    -0.45
     Conservancy
    -0.44
    adpleegd
    -0.44
    POSITIVE LOGITS
    ets
    1.18
    et
    1.09
    eting
    1.07
    ET
    1.04
    ett
    0.96
    ETS
    0.96
    èt
    0.95
    ეტ
    0.94
     et
    0.89
    etto
    0.86
    Activations Density 0.454%

    No Known Activations