© 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. 7-GEMMASCOPE-RES-16K
    11. 15330
    Prev
    Next
    INDEX
    Explanations

    terms related to obstetric and gynecological medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.56
     فريبيس
    -0.55
     ſtand
    -0.54
    yntaxException
    -0.54
     Theſe
    -0.54
     Audiodateien
    -0.54
     pinulongan
    -0.51
    цездатний
    -0.50
     AssemblyCompany
    -0.50
    KURZBESCHREIBUNG
    -0.49
    POSITIVE LOGITS
     ob
    2.63
     Ob
    2.52
    Ob
    2.44
    ob
    2.39
     OB
    2.17
    OB
    2.02
     Obs
    1.67
    obs
    1.38
     Obl
    1.36
     OBL
    1.31
    Activations Density 0.112%

    No Known Activations