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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9761
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal concepts and decisions

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

    commas that appear after specific contextual phrases or clauses.

    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
    adaptiveStyles
    -0.56
     Autorisations
    -0.50
    NameInMap
    -0.48
    igshid
    -0.48
    Externé
    -0.46
    HasForeignKey
    -0.45
    criptors
    -0.43
    atibility
    -0.42
    ývá
    -0.42
    principalTable
    -0.42
    POSITIVE LOGITS
     which
    3.56
    which
    2.42
     Which
    1.97
     WHICH
    1.96
    Which
    1.96
     laquelle
    1.83
    ซึ่ง
    1.81
     które
    1.77
     lequel
    1.77
     которая
    1.71
    Activations Density 3.898%

    No Known Activations