© 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. 14668
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and social justice issues

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

    commas that separate clauses or follow descriptive phrases 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
    клопе
    -0.35
     magát
    -0.34
    avía
    -0.34
    已
    -0.31
     Jego
    -0.31
    Sein
    -0.29
    His
    -0.29
    horesis
    -0.29
    }';
    -0.29
    以
    -0.28
    POSITIVE LOGITS
     he
    1.09
     she
    0.94
    他說
    0.86
    他说
    0.80
    她说
    0.75
     said
    0.75
     officials
    0.73
     Paglinawan
    0.73
     उन्होंने
    0.71
    istoitu
    0.70
    Activations Density 0.282%

    No Known Activations