© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 13069
    Prev
    Next
    INDEX
    Explanations

    the word "actually" 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
    para
    -0.65
    Quel
    -0.65
    nu
    -0.64
    erd
    -0.63
     Ress
    -0.59
    uni
    -0.59
     fermés
    -0.59
    tir
    -0.58
    rad
    -0.58
    Invit
    -0.57
    POSITIVE LOGITS
     actually
    3.02
    actually
    2.73
    Actually
    2.57
     Actually
    2.54
     ACTUALLY
    2.32
     faktiskt
    1.82
     faktisk
    1.76
     sebenarnya
    1.50
     tatsächlich
    1.44
    实际上
    1.21
    Activations Density 0.039%

    No Known Activations