© 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. 16018
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to legal processes and decisions

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

    commas that appear at the end of clauses or before conjunctions in complex sentences.

    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
    ませんが
    -0.41
    からです
    -0.39
    而已
    -0.39
    からだ
    -0.38
    你自己
    -0.34
     Lin
    -0.33
     ES
    -0.33
    的形式
    -0.33
    往
    -0.33
    anga
    -0.33
    POSITIVE LOGITS
     despite
    3.19
    despite
    2.73
     nonostante
    2.64
     несмотря
    2.55
     malgré
    2.53
     Despite
    2.39
    Despite
    2.31
     trotz
    2.31
     apesar
    2.28
     spite
    2.27
    Activations Density 2.208%

    No Known Activations