© 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. 30-GEMMASCOPE-RES-16K
    11. 11817
    Prev
    Next
    INDEX
    Explanations

    references to future actions, plans, or considerations in a discussion

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

    a future time

    np_acts-logits-general · gemini-2.0-flash

    timing or sequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.51
     CreateTagHelper
    -0.50
    WebElementEntity
    -0.48
     становника
    -0.47
    beforeSend
    -0.44
     Italijanski
    -0.43
    팎
    -0.43
    цездатний
    -0.41
    GEBURTSDATUM
    -0.41
     الرياضيه
    -0.41
    POSITIVE LOGITS
     later
    4.09
    later
    3.47
    Later
    3.38
     Later
    3.27
     später
    3.23
     späteren
    2.89
     senere
    2.89
     pozdě
    2.73
     LATER
    2.69
     afterwards
    2.61
    Activations Density 2.350%

    No Known Activations