© 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. 16-GEMMASCOPE-RES-16K
    11. 13384
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate worsening conditions or increasing risks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lindungi
    -0.47
    TargetException
    -0.42
     quedado
    -0.40
     hurtig
    -0.40
    Portale
    -0.40
    pingente
    -0.40
    füllung
    -0.40
     Haring
    -0.39
     kapturem
    -0.39
    moveToFirst
    -0.39
    POSITIVE LOGITS
    worse
    0.74
     worsen
    0.66
     worsened
    0.66
    Worse
    0.65
     worse
    0.64
     Worse
    0.63
     exacerbate
    0.63
     aggravate
    0.63
     exacerbated
    0.61
     aggra
    0.60
    Activations Density 0.231%

    No Known Activations