© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9188
    Prev
    Next
    INDEX
    Explanations

    phrases related to health conditions and their impacts

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

    grammatical constructions using specific verbs like "are" and "being" across various technical and descriptive contexts.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.55
    SharedDtor
    -0.53
     EconPapers
    -0.51
     lieve
    -0.50
     Commando
    -0.49
     ſchon
    -0.49
     Magnitude
    -0.48
     erſt
    -0.48
     Joi
    -0.47
    vrigt
    -0.47
    POSITIVE LOGITS
     ideales
    0.41
     الحره
    0.38
    تقاوى
    0.37
     among
    0.37
    dominant
    0.35
     destaque
    0.33
     dominant
    0.33
     ascenso
    0.33
     uitz
    0.33
     emperador
    0.32
    Activations Density 0.335%

    No Known Activations