© 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. 28-GEMMASCOPE-RES-16K
    11. 2950
    Prev
    Next
    INDEX
    Explanations

    references to categorization and systematic organization

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

    Follows prepositions (by, via, of) or conjunctions (with)

    np_acts-logits-general · gemini-2.0-flash

    preposition followed by descriptive noun

    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
     nôtre
    -0.55
     quelconque
    -0.52
     vôtre
    -0.47
     mantequilla
    -0.47
     fallecido
    -0.47
     colgante
    -0.45
    RegressionTest
    -0.45
     maïs
    -0.45
     llamado
    -0.45
     zmar
    -0.45
    POSITIVE LOGITS
     AssemblyTitle
    0.53
    itemBuilder
    0.43
    UnsafeEnabled
    0.42
    (&:
    0.41
    URLException
    0.40
     nuance
    0.40
     palette
    0.39
     phenotype
    0.39
     anecdote
    0.39
    providedIn
    0.39
    Activations Density 0.677%

    No Known Activations