© 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. 2-GEMMASCOPE-RES-16K
    11. 6447
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "are" 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 @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -1.54
     Majefty
    -1.31
     Jefus
    -1.30
     Houſe
    -1.25
     themſelves
    -1.25
     ſtate
    -1.18
     houſe
    -1.17
     pleaſure
    -1.16
     Efq
    -1.16
     Monfieur
    -1.16
    POSITIVE LOGITS
     am
    1.20
     im
    0.84
     not
    0.80
     a
    0.78
     are
    0.78
    Somos
    0.76
     is
    0.74
     Am
    0.74
     Im
    0.72
     I
    0.72
    Activations Density 0.112%

    No Known Activations