© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 11754
    Prev
    Next
    INDEX
    Explanations

    sequences of events and actions occurring throughout the text

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

    Comes after the word "then"

    np_acts-logits-general · gemini-2.0-flash

    introduces subsequent events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     frattempo
    -0.45
     hvit
    -0.43
    ualaikum
    -0.41
     bowiem
    -0.40
     sibi
    -0.39
    gameserver
    -0.39
    Dichloro
    -0.38
     médias
    -0.37
    êmio
    -0.37
     nevertheless
    -0.36
    POSITIVE LOGITS
     afterward
    0.66
     Daarna
    0.65
     afterwards
    0.65
    Затем
    0.63
    Далее
    0.62
    蚪
    0.60
     Followed
    0.60
     anschließend
    0.59
     Wikimedijinoj
    0.58
     Afterwards
    0.57
    Activations Density 0.423%

    No Known Activations