© 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. 5676
    Prev
    Next
    INDEX
    Explanations

    narrative elements that indicate completion or finished actions

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

    End of a multi-step instruction

    np_acts-logits-general · gemini-2.0-flash

    completion and finality

    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
     ErrInvalid
    -0.54
     leeftijd
    -0.47
     invloed
    -0.45
     protoimpl
    -0.43
     $_(
    -0.43
     väli
    -0.43
     getAge
    -0.43
     slecht
    -0.43
    httphttps
    -0.43
     współpra
    -0.42
    POSITIVE LOGITS
     voila
    0.54
    Voila
    0.49
     Voilà
    0.48
     voilà
    0.47
    Bam
    0.47
     Presto
    0.46
    Voilà
    0.45
    principalTable
    0.45
    Done
    0.44
     presto
    0.44
    Activations Density 0.244%

    No Known Activations