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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 725
    Prev
    Next
    INDEX
    Explanations

    references to individuals, particularly in the context of their actions or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    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
    -2.35
     Monfieur
    -2.33
     myſelf
    -2.26
     itſelf
    -2.20
     purpoſe
    -2.19
     pleaſure
    -2.18
     Houſe
    -2.11
     Theſe
    -2.10
     Anſ
    -2.08
     Majefty
    -2.08
    POSITIVE LOGITS
     she
    2.27
     he
    2.25
     He
    2.02
     She
    1.94
     I
    1.78
     they
    1.68
     They
    1.63
    She
    1.60
     It
    1.58
    she
    1.48
    Activations Density 0.325%

    No Known Activations