© 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. 24-GEMMASCOPE-RES-16K
    11. 907
    Prev
    Next
    INDEX
    Explanations

    phrases that express uncertainty or emotional distress

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

    Incomplete statements or actions

    np_acts-logits-general · gemini-2.0-flash

    unfinished, incomplete, partial

    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
    kiwa
    -0.38
     âme
    -0.36
    ulman
    -0.35
     panahon
    -0.33
    engeance
    -0.33
     hiel
    -0.33
     Analyzed
    -0.32
     respondeu
    -0.32
     rétro
    -0.32
    푼
    -0.32
    POSITIVE LOGITS
     unfinished
    1.23
     incomplete
    1.07
    unfinished
    1.02
     Incomplete
    0.91
    incomplete
    0.91
    Incomplete
    0.87
    Unfinished
    0.85
     partial
    0.81
     completion
    0.78
     finishing
    0.77
    Activations Density 0.493%

    No Known Activations