© 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. 15667
    Prev
    Next
    INDEX
    Explanations

    instances of personal and possessive pronouns

    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
    LookAnd
    -0.96
    +#+#
    -0.71
     AssemblyCulture
    -0.58
    ValueStyle
    -0.57
    SharedCtor
    -0.54
    AsUp
    -0.54
     ब्रेकडाउन
    -0.54
    UnusedPrivate
    -0.54
    setVerticalGroup
    -0.53
    aarrggbb
    -0.52
    POSITIVE LOGITS
    virons
    0.79
    ciety
    0.62
    UMBIA
    0.58
     أنها
    0.56
    VELOP
    0.55
     vznik
    0.55
    quares
    0.55
    urantes
    0.55
    devils
    0.54
    ouncil
    0.54
    Activations Density 0.645%

    No Known Activations