© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 90044
    Prev
    Next
    INDEX
    Explanations

    references to songs and music within the context of a film soundtrack

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

    music, songs, playlists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     detalladas
    -0.35
     computadoras
    -0.35
    WithIOException
    -0.33
     conduite
    -0.33
    viembre
    -0.32
     externas
    -0.32
    Bere
    -0.32
    囗
    -0.32
    iseite
    -0.31
    íncia
    -0.31
    POSITIVE LOGITS
     الرياضيه
    0.57
     playlist
    0.56
     songs
    0.55
    ttino
    0.52
    XmlEnum
    0.51
     song
    0.50
     tracks
    0.50
    hoeddwyd
    0.50
    @[+][
    0.50
     clips
    0.49
    Activations Density 0.014%

    No Known Activations