Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 7459
    Prev
    Next
    INDEX
    Explanations

    references to permission and authorization in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BorderSide
    -0.81
    RTEX
    -0.77
     IService
    -0.68
    MemoryWarning
    -0.67
     ProtoMessage
    -0.65
    enumi
    -0.64
     Савезне
    -0.64
     كومونز
    -0.63
    PYX
    -0.63
     Roskov
    -0.62
    POSITIVE LOGITS
     permission
    1.32
     Permission
    1.14
    permission
    1.08
     approval
    1.07
    autorisation
    1.02
     Approval
    1.02
     permissions
    1.00
     autorisation
    0.97
     authorization
    0.97
    Permission
    0.96
    Activations Density 0.287%

    No Known Activations