© 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. 16-GEMMASCOPE-RES-16K
    11. 12828
    Prev
    Next
    INDEX
    Explanations

    references to local geographic features and historical sites

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nø
    -0.41
     simplifié
    -0.41
     influence
    -0.40
    Cadastro
    -0.39
     content
    -0.35
     influen
    -0.35
     mod
    -0.35
     un
    -0.35
     orientation
    -0.33
    zburg
    -0.33
    POSITIVE LOGITS
     مرئيه
    0.68
    IBOutlet
    0.68
     AssemblyCompany
    0.63
    IsMutable
    0.62
    EndContext
    0.61
    MigrationBuilder
    0.58
     Paglinawan
    0.57
    ]")]
    0.57
    AddTagHelper
    0.56
     disambiguazione
    0.56
    Activations Density 0.236%

    No Known Activations