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. 17-GEMMASCOPE-RES-16K
    6. 10795
    Prev
    Next
    INDEX
    Explanations

    command-based programming structures and their associated conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sizeCache
    -0.85
     Signalez
    -0.65
    IonicModule
    -0.63
     diensten
    -0.62
     réputation
    -0.60
     reputation
    -0.59
     NSCoder
    -0.58
     reputación
    -0.58
     réput
    -0.54
     reputations
    -0.53
    POSITIVE LOGITS
     custom
    0.90
     script
    0.87
     scripting
    0.83
    Script
    0.78
    script
    0.77
    custom
    0.77
     scripted
    0.77
     scripts
    0.76
     Script
    0.76
    Custom
    0.73
    Activations Density 1.198%

    No Known Activations