© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10716
    Prev
    Next
    INDEX
    Explanations

    references to significant days or moments in time

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

    days or times in the future

    np_acts-logits-general · gemini-2.0-flash

    one day events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteTagHelper
    -0.62
     pinulongan
    -0.57
    EndContext
    -0.53
     Италијани
    -0.50
    VYMaps
    -0.48
     CreateTagHelper
    -0.48
    şiv
    -0.47
     Audiodateien
    -0.46
    AISSEE
    -0.45
    providedIn
    -0.43
    POSITIVE LOGITS
    有一天
    0.69
     someday
    0.59
     روزی
    0.57
     pernah
    0.56
    Someday
    0.53
     sometime
    0.52
     Sometime
    0.52
     ooit
    0.52
     egyszer
    0.51
    Someone
    0.50
    Activations Density 0.324%

    No Known Activations