© 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. 4543
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly in contexts involving mathematical operations or statistics

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

    Numbers followed by arithmetic symbols

    np_acts-logits-general · gemini-2.0-flash

    numbers and operators

    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
     feroit
    -0.54
    Бахар
    -0.47
     []:
    -0.47
     caballo
    -0.45
     proprement
    -0.44
     pouvoit
    -0.44
     étoit
    -0.43
     étroite
    -0.43
     chercheurs
    -0.41
     sœur
    -0.41
    POSITIVE LOGITS
    AISSEE
    0.55
    AndEndTag
    0.54
    exitRule
    0.52
    fjspx
    0.52
    InputBorder
    0.50
     fos
    0.49
     незавершена
    0.49
    fos
    0.48
     foss
    0.46
     fob
    0.45
    Activations Density 0.802%

    No Known Activations