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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 58357
    Prev
    Next
    INDEX
    Explanations

    terms related to mixing or blending different elements, particularly in contexts involving music or media

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

    mixing, mastering, and blending

    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
    fortawesome
    -0.62
    Dermott
    -0.60
    noopener
    -0.59
    urlopen
    -0.58
    defineProperty
    -0.56
    callable
    -0.56
     statusCode
    -0.54
     חיצוניים
    -0.54
    Facades
    -0.52
    Leopold
    -0.52
    POSITIVE LOGITS
     mix
    1.22
     Mix
    1.16
    Mix
    1.13
    mix
    1.11
     MIX
    1.09
     mixer
    1.01
    MIX
    1.00
     mixing
    0.97
     mixes
    0.96
     Mixer
    0.92
    Activations Density 0.020%

    No Known Activations