© 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. 35-GEMMASCOPE-RES-16K
    11. 12257
    Prev
    Next
    INDEX
    Explanations

    expressions of positivity and appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.85
     resourceCulture
    -0.69
     HasFactory
    -0.67
     ſch
    -0.61
     désolés
    -0.60
     CreateTagHelper
    -0.60
    FDRE
    -0.59
    NameInMap
    -0.59
     pleaſure
    -0.58
    ArgumentParser
    -0.58
    POSITIVE LOGITS
     freakin
    0.78
     freaking
    0.74
     insane
    0.65
     legit
    0.63
     hella
    0.63
     epic
    0.60
     fucking
    0.59
     fuckin
    0.57
     killer
    0.55
     frig
    0.53
    Activations Density 0.306%

    No Known Activations