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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 14731
    Prev
    Next
    INDEX
    Explanations

    references to engineering and related academic fields

    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
     Attraction
    -0.79
     ſtate
    -0.78
    glBindTexture
    -0.76
     Sotheby
    -0.76
     vôtre
    -0.76
    antMatchers
    -0.75
    fastjson
    -0.74
     Clapton
    -0.73
     Lovato
    -0.73
    ntos
    -0.73
    POSITIVE LOGITS
     engineers
    1.49
     engineering
    1.48
     engineer
    1.44
     Engineering
    1.33
    engineering
    1.32
    Engineers
    1.31
    Engineering
    1.27
     Engineers
    1.24
    engineer
    1.19
     ENGINEERING
    1.19
    Activations Density 0.081%

    No Known Activations