© 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-2-9B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 8740
    Prev
    Next
    INDEX
    Explanations

    references to possessive pronouns and their relations to identity and family

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <?
    -0.49
    CodeAttribute
    -0.42
     OnInit
    -0.38
     ExecuteAsync
    -0.38
    PhysRev
    -0.38
    PreInfinity
    -0.37
     FixedUpdate
    -0.37
    ArrowToggle
    -0.36
    CodeAnalysis
    -0.36
     Plu
    -0.35
    POSITIVE LOGITS
     miniaturka
    0.50
     Exactos
    0.48
     wiedzy
    0.48
    agisse
    0.48
    pecabe
    0.48
     parachoque
    0.47
     자신의
    0.47
     løpet
    0.47
    ตัวเอง
    0.46
     increí
    0.46
    Activations Density 0.721%

    No Known Activations