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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 11887
    Prev
    Next
    INDEX
    Explanations

    discussions related to tone in various contexts

    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
    terdam
    -0.73
    Biografia
    -0.69
    GoogleApiClient
    -0.69
    couver
    -0.67
    PerformLayout
    -0.66
    routeProvider
    -0.64
    guez
    -0.63
    逅
    -0.63
    tershire
    -0.61
    μβρίου
    -0.60
    POSITIVE LOGITS
     tone
    3.23
     Tone
    3.01
    tone
    2.85
    Tone
    2.75
     tones
    2.61
     Tones
    2.55
    tones
    2.13
    TONE
    2.09
     toned
    1.86
    toned
    1.84
    Activations Density 0.075%

    No Known Activations