© 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. 33-GEMMASCOPE-RES-16K
    11. 1961
    Prev
    Next
    INDEX
    Explanations

    phrases related to regulatory or approval processes in a formal context

    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
    __":
    -0.45
     виправивши
    -0.39
    __':
    -0.39
     مُعرِّف
    -0.38
    providedIn
    -0.36
    깝
    -0.33
    FormUrlEncoded
    -0.33
    RegistryLite
    -0.33
     législation
    -0.32
    MessageTagHelper
    -0.31
    POSITIVE LOGITS
     creation
    1.63
     removal
    1.41
     introduction
    1.36
     adoption
    1.30
     establishment
    1.29
     formation
    1.28
     issuance
    1.27
     completion
    1.25
     inclusion
    1.21
     elimination
    1.21
    Activations Density 2.932%

    No Known Activations