© 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. 34-GEMMASCOPE-RES-16K
    11. 13761
    Prev
    Next
    INDEX
    Explanations

    references to legal caution and the impact of legal decisions on individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.59
     sincerity
    -0.58
     humb
    -0.53
     reliably
    -0.50
     succinctly
    -0.48
    tangentMode
    -0.47
    じっくり
    -0.46
    MigrationBuilder
    -0.46
    TagHelper
    -0.46
    readystatechange
    -0.46
    POSITIVE LOGITS
     unnecessary
    1.73
     unnecessarily
    1.59
     unwarranted
    1.55
     unjustified
    1.45
     inneces
    1.43
     inappropriate
    1.42
     needlessly
    1.40
     unreasonable
    1.37
     unreasonably
    1.27
     pointless
    1.24
    Activations Density 1.315%

    No Known Activations