© 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 EvalsExportsinterp-engineNEWAPI 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. 116240
    Prev
    Next
    INDEX
    Explanations

    references to voices and vocal elements in various contexts

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

    voice of

    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
     Trenton
    -0.49
     It
    -0.44
     Had
    -0.41
     Mall
    -0.41
     culturali
    -0.41
     Old
    -0.41
     fact
    -0.41
     matrimonial
    -0.40
     Het
    -0.39
     Dunn
    -0.39
    POSITIVE LOGITS
    voice
    1.13
    Voice
    1.13
     Voice
    1.12
     voice
    1.10
     VOICE
    1.03
     voic
    0.91
    VOICE
    0.90
    Voz
    0.82
     Voices
    0.82
    Voices
    0.81
    Activations Density 0.010%

    No Known Activations