© 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. 22-GEMMASCOPE-RES-16K
    11. 5883
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences with service and assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Anlass
    -0.46
    vician
    -0.43
    Примітки
    -0.43
    terung
    -0.42
    setContentView
    -0.40
    ::::::::::::::::
    -0.38
     isolada
    -0.36
    Халык
    -0.36
    formik
    -0.36
    Lähteet
    -0.36
    POSITIVE LOGITS
     defaultstate
    0.76
    Jereo
    0.44
     transfieras
    0.42
     
    0.40
    contentLoaded
    0.40
     &___
    0.39
     himself
    0.39
     gentleman
    0.38
     الرياضيه
    0.38
     encyclo
    0.37
    Activations Density 0.069%

    No Known Activations