© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 11027
    Prev
    Next
    INDEX
    Explanations

    pronouns, particularly variations of "I"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ve
    -0.52
    ます
    -0.51
    اں
    -0.45
    st
    -0.44
    dan
    -0.42
    ">//
    -0.42
    le
    -0.41
    ない
    -0.41
    enumi
    -0.41
    na
    -0.40
    POSITIVE LOGITS
     defaultstate
    0.64
     iVar
    0.60
    ніципалі
    0.55
     NSCoder
    0.53
    withIdentifier
    0.52
    Geplaatst
    0.51
    kå
    0.48
     fubject
    0.47
     estekak
    0.43
    river
    0.43
    Activations Density 0.310%

    No Known Activations