© 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. 18-GEMMASCOPE-RES-16K
    11. 8363
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to singing and musical activities

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

    singing or songs

    np_acts-logits-general · gemini-2.0-flash

    singing songs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PMailer
    -0.60
    RTSC
    -0.58
     consultato
    -0.57
     kasarigan
    -0.55
     négociations
    -0.53
    uttosto
    -0.53
     khai
    -0.52
    ScopeManager
    -0.51
    tä
    -0.51
    Referencies
    -0.49
    POSITIVE LOGITS
     lyrics
    1.19
     singing
    1.15
     sung
    1.06
     sings
    1.05
     sing
    1.02
     karaoke
    1.00
     melody
    0.88
     Lyrics
    0.87
     lyric
    0.85
     song
    0.85
    Activations Density 0.079%

    No Known Activations