© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 12002
    Prev
    Next
    INDEX
    Explanations

    formulaic expressions or mathematical notations used in complex equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nonUne
    -0.59
     BoxFit
    -0.58
    bootstrapcdn
    -0.55
     للمعارف
    -0.54
    StoryboardSegue
    -0.52
    fromnode
    -0.50
     AssemblyCulture
    -0.49
     '\\;'
    -0.48
     насељу
    -0.47
     AssemblyCompany
    -0.47
    POSITIVE LOGITS
    <bos>
    0.75
    [toxicity=0]
    0.43
     isNameExpr
    0.42
     labial
    0.42
     beſt
    0.42
    smile
    0.42
    </sup>
    0.42
     }}$}
    0.42
     pila
    0.41
    

    0.41
    Activations Density 0.585%

    No Known Activations