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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 16331
    Prev
    Next
    INDEX
    Explanations

    instances of the word "voice" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tembelea
    -0.73
    ✷
    -0.73
     bezeichneter
    -0.67
    RTDA
    -0.66
     monasteries
    -0.62
    chery
    -0.62
    OGND
    -0.62
    Datuak
    -0.61
     decker
    -0.61
    kheim
    -0.61
    POSITIVE LOGITS
     voice
    3.70
     Voice
    3.23
    voice
    3.16
    Voice
    3.09
     voices
    3.00
     VOICE
    3.00
    VOICE
    2.55
    voices
    2.49
     Voices
    2.43
     voz
    2.35
    Activations Density 0.038%

    No Known Activations