© 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. 2-GEMMASCOPE-RES-16K
    11. 13336
    Prev
    Next
    INDEX
    Explanations

    references to statistical moments and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.55
     للمعارف
    -0.47
    EndContext
    -0.44
    adaptiveStyles
    -0.40
    <bos>
    -0.40
    ActionPerformed
    -0.40
    ValueStyle
    -0.40
    :]:
    -0.39
    VIAF
    -0.39
    RectangleBorder
    -0.38
    POSITIVE LOGITS
     defect
    1.08
     defects
    1.05
     Defect
    1.00
     Defects
    0.98
    Defect
    0.84
     flaw
    0.84
     flaws
    0.81
     defectos
    0.79
    defect
    0.77
     défauts
    0.63
    Activations Density 0.171%

    No Known Activations