© 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. 9954
    Prev
    Next
    INDEX
    Explanations

    phrases expressing negative sentiment or doubt

    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
     is
    -0.61
    i
    -0.60
    a
    -0.59
    s
    -0.56
    tels
    -0.56
    k
    -0.56
    y
    -0.54
     ist
    -0.53
    b
    -0.53
    l
    -0.53
    POSITIVE LOGITS
     wouldn
    1.82
    wouldn
    1.69
     Wouldn
    1.51
    Wouldn
    1.35
     wouldnt
    1.32
     shouldn
    1.16
     Shouldn
    1.14
     unlikely
    1.11
     GenerationType
    1.07
    CloseOperation
    1.03
    Activations Density 0.060%

    No Known Activations