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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 8182
    Prev
    Next
    INDEX
    Explanations

    references to legal claims and court rulings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    legal citation formatting and references.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beziehungs
    -0.83
     například
    -0.66
     television
    -0.61
     أيضًا
    -0.57
    件事情
    -0.57
     ſind
    -0.55
    říklad
    -0.54
     eighty
    -0.54
     Incorporated
    -0.53
    ًا
    -0.53
    POSITIVE LOGITS
     ppl
    1.20
     govt
    1.14
     Univ
    1.09
     Govt
    1.05
     yrs
    1.02
     např
    1.00
     Assn
    0.94
     др
    0.91
     Thx
    0.90
     yg
    0.90
    Activations Density 2.722%

    No Known Activations