© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3399
    Prev
    Next
    INDEX
    Explanations

    references to music albums and their details

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

    details about albums, such as album name, track listings, release dates, and album descriptions.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ScopeManager
    -0.54
     CreateTagHelper
    -0.48
    épend
    -0.46
    usercontent
    -0.46
    __;
    -0.46
    BagConstraints
    -0.46
    saraba
    -0.44
    ɵɵelementEnd
    -0.43
    SerializedSize
    -0.43
    encodeWith
    -0.43
    POSITIVE LOGITS
     album
    0.88
     albums
    0.73
     Album
    0.68
    album
    0.61
    Album
    0.61
     álbum
    0.61
    Albums
    0.59
     ALBUM
    0.58
     propOrder
    0.57
     альбом
    0.54
    Activations Density 0.074%

    No Known Activations