Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 2426
    Prev
    Next
    INDEX
    Explanations

    terms associated with file management and conversion in audio software

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

    Creating and managing music files/playlists

    np_acts-logits-general · gemini-2.0-flash

    create playlist

    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
    PostBack
    -0.51
    scalatest
    -0.48
     createSprite
    -0.46
     Schwert
    -0.45
     typewriter
    -0.45
     Schrift
    -0.44
    ("")]
    -0.44
    TextFormField
    -0.43
     πέ
    -0.43
    WebServlet
    -0.43
    POSITIVE LOGITS
     songs
    1.25
     playlists
    1.24
     song
    1.23
     playlist
    1.23
     tracks
    1.10
     artist
    1.10
     album
    1.09
    song
    1.09
     Songs
    1.08
     Song
    1.06
    Activations Density 0.226%

    No Known Activations