© 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. 33-GEMMASCOPE-RES-16K
    11. 7632
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to medical or psychological diagnoses and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConverterFactory
    -0.42
    requestCode
    -0.37
    resultCode
    -0.36
    Clik
    -0.35
     Roskov
    -0.34
    PRINCIP
    -0.34
    setItems
    -0.33
     الدوري
    -0.32
    PLOT
    -0.32
     HttpNotFound
    -0.32
    POSITIVE LOGITS
     terminology
    1.86
     term
    1.80
     istilah
    1.59
     terms
    1.55
     phrase
    1.52
    Terminology
    1.41
     término
    1.41
     términos
    1.40
     Terminology
    1.40
     phrases
    1.38
    Activations Density 0.846%

    No Known Activations