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. 1319
    Prev
    Next
    INDEX
    Explanations

    references to different contexts in a structured format

    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
     uſed
    -0.84
    omla
    -0.81
    SBATCH
    -0.79
    IonicModule
    -0.79
     Shakspeare
    -0.79
     Efq
    -0.78
     DELLE
    -0.78
    ModelAdmin
    -0.78
    #+#
    -0.76
    ✨:
    -0.75
    POSITIVE LOGITS
     context
    1.69
    Context
    1.66
     Context
    1.65
     useContext
    1.63
     contexts
    1.60
    context
    1.57
     CONTEXT
    1.55
    CONTEXT
    1.47
     getContext
    1.34
     ctx
    1.33
    Activations Density 0.036%

    No Known Activations