© 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. 28-GEMMASCOPE-RES-16K
    11. 5987
    Prev
    Next
    INDEX
    Explanations

    structure and syntax in programming code snippets, particularly involving output statements and data input

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

    or phrases followed by dialogue

    np_acts-logits-general · gemini-2.0-flash

    reporting speech

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SBATCH
    -0.48
     Вікіпе
    -0.45
    istoitu
    -0.43
    Tembelea
    -0.42
     Arhivirano
    -0.42
    xnn
    -0.41
    __*/
    -0.41
    weetened
    -0.39
     Rope
    -0.38
     nakalista
    -0.38
    POSITIVE LOGITS
     saying
    1.31
    saying
    1.07
     berkata
    0.92
     Saying
    0.90
     said
    0.89
     diciendo
    0.88
     sayin
    0.86
    Saying
    0.86
     says
    0.83
     say
    0.78
    Activations Density 0.314%

    No Known Activations