© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 12739
    Prev
    Next
    INDEX
    Explanations

    specific age-related information about individuals, particularly focusing on the years and ages stated

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addCriterion
    -0.66
    haikusbot
    -0.54
     Autorisations
    -0.49
    Nimbus
    -0.46
     HasFactory
    -0.46
    cinfo
    -0.45
    situ
    -0.44
     technics
    -0.43
    obbies
    -0.43
     corridors
    -0.43
    POSITIVE LOGITS
     &___
    0.57
    IntoConstraints
    0.43
     تعدى
    0.41
    ंदीखरीदारी
    0.40
     joaat
    0.38
    appcompat
    0.37
    AndView
    0.37
    principalColumn
    0.37
     unmarried
    0.36
     '\\;'
    0.36
    Activations Density 0.145%

    No Known Activations