© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4410
    Prev
    Next
    INDEX
    Explanations

    numerical data and financial figures

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

    Values after minus signs or periods

    np_acts-logits-general · gemini-2.0-flash

    numbers and percentages

    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
     rapat
    -0.37
     palais
    -0.34
     bilen
    -0.33
    GTCX
    -0.32
     refroid
    -0.32
     fondateur
    -0.32
     defaultstate
    -0.32
     Política
    -0.31
     dispozici
    -0.30
    nativeElement
    -0.29
    POSITIVE LOGITS
     للمعارف
    0.54
     ब्रेकडाउन
    0.53
    featureID
    0.52
    principalTable
    0.52
    CloseOperation
    0.50
    Personendaten
    0.50
    ьажоргаш
    0.49
     utafitiHapana
    0.47
    newArrayList
    0.46
     محفوظة
    0.45
    Activations Density 0.819%

    No Known Activations