© 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. 7694
    Prev
    Next
    INDEX
    Explanations

    references to medical and scientific organizations and studies

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

    Tokens starting with a capital letter

    np_acts-logits-general · gemini-2.0-flash

    Dejal, PRRSV, edges and, 10, . Blo

    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
     piatta
    -0.40
     заме
    -0.36
     thread
    -0.36
     ra
    -0.36
     failure
    -0.36
     complicated
    -0.35
    forRoot
    -0.35
     format
    -0.35
     bik
    -0.35
     strip
    -0.35
    POSITIVE LOGITS
     purpoſe
    0.54
     Houſe
    0.53
    enderror
    0.50
     houſe
    0.50
    queryInterface
    0.49
     myſelf
    0.48
    AddTagHelper
    0.47
     Anſ
    0.47
    ьаж
    0.47
    ########.
    0.47
    Activations Density 0.534%

    No Known Activations