© 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. 2685
    Prev
    Next
    INDEX
    Explanations

    instances of error messages and problem descriptions related to software

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

    non-English text, particularly Japanese and Korean characters and phrases.

    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
    だが
    -0.93
    だったが
    -0.85
    であるが
    -0.79
    ようだ
    -0.75
     were
    -0.71
     있다
    -0.67
     것이다
    -0.66
     한다
    -0.62
    したが
    -0.60
    이다
    -0.59
    POSITIVE LOGITS
    您
    0.70
    您的
    0.62
    تقاوى
    0.61
     Mr
    0.60
    ;");
    0.60
     您
    0.60
     σας
    0.59
     vostri
    0.59
    ค่ะ
    0.59
    ครับ
    0.59
    Activations Density 0.006%

    No Known Activations