© 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. 33-GEMMASCOPE-RES-16K
    11. 10562
    Prev
    Next
    INDEX
    Explanations

    references to software components or programming instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Waray
    -0.44
    AndEndTag
    -0.44
    relevant
    -0.40
    piram
    -0.40
    redient
    -0.38
     involuntarily
    -0.38
    靂
    -0.38
    Slf
    -0.38
     relevant
    -0.37
    DISPATCH
    -0.37
    POSITIVE LOGITS
    yntaxException
    0.56
    webElementGuid
    0.55
    Enllaços
    0.52
    Manbalar
    0.52
     IBOutlet
    0.48
     HasFactory
    0.48
    AISSEE
    0.45
    Autoritní
    0.45
    Cyfeiriadau
    0.44
     SEDS
    0.43
    Activations Density 1.876%

    No Known Activations