© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 27-GEMMASCOPE-RES-16K
    6. 9359
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a lack of information or knowledge related to healthcare procedures and public health data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hoped
    -0.34
     hopefully
    -0.33
    hopefully
    -0.32
     pad
    -0.32
    pad
    -0.32
     hoping
    -0.31
     hopes
    -0.31
    पया
    -0.31
     indir
    -0.30
     Ser
    -0.30
    POSITIVE LOGITS
     autorytatywna
    0.73
     fubject
    0.68
     <<<<<<<<<<<<<<
    0.66
    ftagPool
    0.65
     uſe
    0.65
     myſelf
    0.63
    ſchaft
    0.62
    ſelves
    0.62
    ⟬
    0.61
     ſtate
    0.60
    Activations Density 0.627%

    No Known Activations