© 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. 19-GEMMASCOPE-RES-16K
    11. 11108
    Prev
    Next
    INDEX
    Explanations

    questions and statements of uncertainty or inquiry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -1.31
     myſelf
    -1.19
     ſche
    -1.15
    ſelves
    -1.14
     Majefty
    -1.12
     itſelf
    -1.08
     themſelves
    -1.06
     ſeveral
    -1.06
     ſever
    -1.03
    ſelf
    -1.03
    POSITIVE LOGITS
     it
    1.19
     the
    1.01
     a
    0.92
     this
    0.84
     he
    0.84
     happens
    0.79
     we
    0.78
     kind
    0.75
     their
    0.74
     they
    0.73
    Activations Density 0.114%

    No Known Activations