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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-GEMMASCOPE-RES-16K
    6. 12511
    Prev
    Next
    INDEX
    Explanations

    terms related to deployment processes or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Farn
    -0.81
    ImageContext
    -0.77
     onOptions
    -0.77
     Cerr
    -0.76
    fromCharCode
    -0.73
     Pell
    -0.73
    __":
    -0.72
    uncher
    -0.69
    בודה
    -0.69
    antMatchers
    -0.68
    POSITIVE LOGITS
     Deploy
    1.27
     deployed
    1.26
     Deployment
    1.25
     deployment
    1.19
     deploy
    1.19
    deploy
    1.17
    deployed
    1.17
     deploying
    1.17
    Deploy
    1.16
     Dep
    1.15
    Activations Density 0.101%

    No Known Activations