© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 16305
    Prev
    Next
    INDEX
    Explanations

    musical compositions and references to composers or their works

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

    Classical music composers or compositions

    np_acts-logits-general · gemini-2.0-flash

    musical forms and composers

    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
     ProtoMessage
    -0.81
    IsMutable
    -0.65
    érience
    -0.61
    twimg
    -0.59
     raiſ
    -0.59
     Monfieur
    -0.57
     deſt
    -0.57
     segíts
    -0.57
    ReusableCell
    -0.56
    PRNewswire
    -0.55
    POSITIVE LOGITS
     Suite
    0.66
     suite
    0.64
    Theme
    0.61
    Suite
    0.59
     theme
    0.58
     Rondo
    0.58
     Theme
    0.58
     SUITE
    0.55
     Schumann
    0.54
     themes
    0.54
    Activations Density 0.087%

    No Known Activations