Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16117
    Prev
    Next
    INDEX
    Explanations

    educational qualifications and programs

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

    Master's or graduate level degrees

    np_acts-logits-general · gemini-2.0-flash

    university degrees and graduate programs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    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
     teenagers
    -0.45
     teenager
    -0.44
     teenage
    -0.43
    teenage
    -0.41
     beginnetje
    -0.41
     defaultstate
    -0.40
     teen
    -0.40
    MigrationBuilder
    -0.40
     youngsters
    -0.39
    atschappij
    -0.39
    POSITIVE LOGITS
     Masters
    0.63
     certificate
    0.57
     masters
    0.57
     specialization
    0.55
     Graduate
    0.55
     Master
    0.55
     Certificate
    0.54
     Grad
    0.53
     program
    0.53
     postgraduate
    0.53
    Activations Density 0.063%

    No Known Activations