© 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. 35-GEMMASCOPE-RES-16K
    11. 5374
    Prev
    Next
    INDEX
    Explanations

    items related to legal terminology and case details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eighty
    -1.18
     seventy
    -1.13
     fifty
    -1.09
     sixty
    -1.08
     ninety
    -1.06
     forty
    -1.06
     thirty
    -0.99
     eighteen
    -0.98
     Eighty
    -0.98
     twenty
    -0.96
    POSITIVE LOGITS
     ½
    0.59
    第
    0.57
    GEBURTS
    0.44
     AssemblyTitle
    0.44
     
    0.44
     externi
    0.43
     BoxDecoration
    0.40
     ¾
    0.40
     ¼
    0.39
    UnsafeEnabled
    0.39
    Activations Density 0.628%

    No Known Activations