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. 20-GEMMASCOPE-RES-16K
    6. 7524
    Prev
    Next
    INDEX
    Explanations

    technical terms and specific programming language elements related to PHP and databases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vers
    -0.40
    "}},
    -0.40
    )}>
    -0.39
     Vers
    -0.35
    JAR
    -0.35
    油
    -0.33
    めで
    -0.33
     làm
    -0.32
     Job
    -0.31
    画
    -0.31
    POSITIVE LOGITS
     Majefty
    1.14
    ſelf
    1.12
    moiselle
    1.04
     purpoſe
    1.02
    Xna
    0.97
     greateſt
    0.92
    
    0.92
     незавершена
    0.92
    SBATCH
    0.92
     Signalez
    0.92
    Activations Density 0.076%

    No Known Activations