© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 6121
    Prev
    Next
    INDEX
    Explanations

    words related to pathogens and their effects on hosts

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

    Follows specific terms ("pathogen", pronouns, "user," "blacks")

    np_acts-logits-general · gemini-2.0-flash

    pathogen, students, you, him, generations, blacks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ifers
    -0.42
    aute
    -0.42
     fit
    -0.42
    стоин
    -0.41
    ⤹
    -0.41
     heritage
    -0.40
     Knowledge
    -0.40
     patents
    -0.40
     Fit
    -0.39
    یرات
    -0.39
    POSITIVE LOGITS
    enderror
    0.74
    出版年
    0.72
    tagHelperRunner
    0.69
    
    0.65
    reportWebVitals
    0.65
    verifyException
    0.65
    +#+#
    0.61
     AssemblyCulture
    0.59
    contentLoaded
    0.56
    EndContext
    0.56
    Activations Density 0.322%

    No Known Activations