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-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 9873
    Prev
    Next
    INDEX
    Explanations

    phrases related to qualifications and educational achievements, particularly regarding degrees and their significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ParallelGroup
    -0.73
    XmlElement
    -0.68
    LEncoder
    -0.68
    gonic
    -0.64
     genoux
    -0.57
     ExecuteAsync
    -0.57
    LabelTagHelper
    -0.57
    uxxxx
    -0.57
    ValueStyle
    -0.53
    islation
    -0.53
    POSITIVE LOGITS
     acquired
    0.55
     acquiring
    0.55
     acquire
    0.54
     aspi
    0.53
     traits
    0.52
     citizenship
    0.50
     attain
    0.49
     lyst
    0.49
     resourceCulture
    0.49
     eligibility
    0.49
    Activations Density 0.471%

    No Known Activations