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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 104
    Prev
    Next
    INDEX
    Explanations

    patterns or structures in non-verbal content, such as markers or breaks in text

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

    technical or numerical details about musical instruments and sound.

    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
    UrlResolution
    -0.61
    RenderAtEndOf
    -0.60
     kasarigan
    -0.56
     فريبيس
    -0.53
    FormTagHelper
    -0.51
    ScopeManager
    -0.48
    WindowConstants
    -0.48
    UnitTesting
    -0.47
    estic
    -0.47
     */;
    -0.47
    POSITIVE LOGITS
     chords
    0.44
     harmonies
    0.38
     trầm
    0.36
     músicos
    0.36
     Вікі
    0.36
    ➯
    0.35
    eapples
    0.35
    ⇛
    0.35
     chord
    0.34
     shaded
    0.33
    Activations Density 0.069%

    No Known Activations