© 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. 10036
    Prev
    Next
    INDEX
    Explanations

    phrases indicating temporal relationships and conditions

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

    "Prior to" or "Before"

    np_acts-logits-general · gemini-2.0-flash

    before or prior to an event

    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
     nakalista
    -0.73
    rungsseite
    -0.63
     ujednoznacz
    -0.60
    pogon
    -0.60
    Portale
    -0.59
    NOPQRST
    -0.57
    BibitemShut
    -0.57
    السكان
    -0.57
    RTLR
    -0.56
    AddTagHelper
    -0.56
    POSITIVE LOGITS
    During
    0.46
    Once
    0.45
     During
    0.44
     Upon
    0.44
     Once
    0.41
    IsContent
    0.40
    With
    0.40
    Upon
    0.39
    After
    0.38
    ammans
    0.36
    Activations Density 1.120%

    No Known Activations