© 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. 766
    Prev
    Next
    INDEX
    Explanations

    reflexive pronouns referring to entities (such as "himself," "itself," and "themselves")

    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
     Pitman
    -0.65
    <eos>
    -0.57
     McIn
    -0.57
    er
    -0.56
    Parcelize
    -0.56
    eri
    -0.55
    rad
    -0.54
    位の
    -0.54
    )):
    -0.54
    radial
    -0.53
    POSITIVE LOGITS
     himself
    2.82
     Himself
    2.75
     itself
    2.75
    itself
    2.72
     herself
    2.69
     themselves
    2.64
    themselves
    2.58
    himself
    2.55
     Itself
    2.54
    herself
    2.46
    Activations Density 0.054%

    No Known Activations