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

    Neuronpedia

    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. 28-GEMMASCOPE-RES-16K
    11. 4257
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of individuals, organizations, and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by suffixes

    np_acts-logits-general · gemini-2.0-flash

    proper nouns and entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    씩
    -0.40
     spalle
    -0.39
     fieltro
    -0.34
     appunto
    -0.34
    iligten
    -0.34
     táctil
    -0.33
    verständlich
    -0.33
    __':
    -0.33
     רבה
    -0.33
     zufolge
    -0.33
    POSITIVE LOGITS
    ########.
    0.88
     propOrder
    0.82
     ModelExpression
    0.78
    rungsseite
    0.78
    ArrowToggle
    0.73
     <<<<<<<<<<<<<<
    0.72
    AddTagHelper
    0.69
    LookAnd
    0.69
     typelib
    0.68
    DeleteBehavior
    0.68
    Activations Density 1.157%

    No Known Activations