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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11060
    Prev
    Next
    INDEX
    Explanations

    references to the 1970s television shows "The Six Million Dollar Man" and "The Bionic Woman", particularly the bionic sound effects from the show.

    oai_token-act-pair · gemini-2.0-flash

    sounds

    np_max-act-logits · gemini-2.0-flash

    references to sound or auditory experiences associated with specific events or scenarios.

    oai_token-act-pair · gpt-4o-miniTriggered by @bje1126

    sounds

    np_max-act-logits · gpt-4o-miniTriggered by @bje1126
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    terase
    -0.57
     Normdatei
    -0.56
    ละเอียด
    -0.46
    ModelSerializer
    -0.46
     Straf
    -0.46
    AccessFile
    -0.45
     Allociné
    -0.44
     يتيمه
    -0.44
     Tugend
    -0.43
    AsUp
    -0.43
    POSITIVE LOGITS
     sounds
    1.51
     sound
    1.49
    sounds
    1.34
     SOUND
    1.33
     noises
    1.32
    sound
    1.30
     sounded
    1.27
     loud
    1.25
    Sound
    1.21
     sounding
    1.21
    Activations Density 4.794%

    No Known Activations