© 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. 14028
    Prev
    Next
    INDEX
    Explanations

    references to academic degrees and qualifications

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

    academic credentials and educational degrees.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    references to academic credentials, particularly advanced degrees (PhD, master's, doctorate) and their associated fields of study.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    mentions of formal education and professional credentials, especially academic degrees, titles, and institutional affiliations.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    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
     дописавши
    -0.44
    ècie
    -0.42
    Билгалдахарш
    -0.38
    BIÉN
    -0.37
     sırasında
    -0.37
    सन्दर्भ
    -0.36
    PageIndex
    -0.36
     počas
    -0.35
    rrggbb
    -0.35
     Teufel
    -0.35
    POSITIVE LOGITS
     בתח
    0.84
    ด้าน
    0.69
     bidang
    0.65
     in
    0.63
    antMatchers
    0.58
     области
    0.57
     về
    0.57
     specializing
    0.56
     Bidang
    0.55
    featureID
    0.53
    Activations Density 0.465%

    No Known Activations