© 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. 4-GEMMASCOPE-RES-16K
    11. 10763
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns in the context of subjects and their relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     True
    -0.54
    μβ
    -0.53
     true
    -0.53
    ])))
    -0.50
     relative
    -0.48
     Ger
    -0.47
    iss
    -0.47
     lowercase
    -0.46
    ̣i
    -0.46
     sak
    -0.46
    POSITIVE LOGITS
     AssemblyCulture
    0.97
    adaptiveStyles
    0.86
     kteří
    0.79
    Gön
    0.78
    setVerticalGroup
    0.74
     compléter
    0.72
    <_>
    0.68
    BindingResult
    0.66
     difficiles
    0.66
    RenderAtEndOf
    0.66
    Activations Density 0.489%

    No Known Activations