© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 1977
    Prev
    Next
    INDEX
    Explanations

    discussions related to government spending and healthcare programs

    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
    InjectAttribute
    -1.01
    MigrationBuilder
    -0.91
     OMITBAD
    -0.67
     theils
    -0.63
     fathoms
    -0.62
    RTEX
    -0.61
     Biographical
    -0.58
    brigens
    -0.58
     hummingbird
    -0.56
     smtplib
    -0.55
    POSITIVE LOGITS
    GeneratedCode
    0.52
    AutoScale
    0.51
    >",
    
    0.50
    PERATURE
    0.47
     Nieder
    0.47
    '])){
    
    0.46
    供
    0.46
    CURLOPT
    0.44
    mover
    0.44
    Trag
    0.44
    Activations Density 0.495%

    No Known Activations