© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 8125
    Prev
    Next
    INDEX
    Explanations

    concepts or topics related to breadth or inclusivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Спасылкі
    -0.49
     discriminated
    -0.46
     disgusting
    -0.44
     freakin
    -0.44
     Arkivert
    -0.43
     wachsen
    -0.42
     gustó
    -0.42
     grinning
    -0.42
     petting
    -0.42
    Mommy
    -0.42
    POSITIVE LOGITS
    Broad
    0.98
     Broad
    0.96
     broad
    0.93
    broad
    0.87
     BROAD
    0.76
    BROAD
    0.65
    AddTagHelper
    0.63
    __(/*!
    0.62
     Bro
    0.61
     broader
    0.60
    Activations Density 0.242%

    No Known Activations