© 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. 28-GEMMASCOPE-RES-16K
    11. 9031
    Prev
    Next
    INDEX
    Explanations

    relationships between temperatures, pressures, and their effects on processes or materials

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

    limits/rates ("maximum", "critical", etc.)

    np_acts-logits-general · gemini-2.0-flash

    values below critical thresholds

    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
    CreateMap
    -0.37
    läng
    -0.35
     continuidad
    -0.34
    évaluateur
    -0.33
     variedad
    -0.33
    図
    -0.33
     Borel
    -0.31
     poster
    -0.31
     varietà
    -0.31
    Хро
    -0.31
    POSITIVE LOGITS
     threshold
    0.81
     minimum
    0.73
     critical
    0.73
     seuil
    0.72
     maximum
    0.69
     optimum
    0.69
    threshold
    0.66
     Threshold
    0.63
     CRITICAL
    0.63
    Minimum
    0.62
    Activations Density 1.247%

    No Known Activations