© 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. 25-GEMMASCOPE-RES-16K
    6. 4590
    Prev
    Next
    INDEX
    Explanations

    terms related to conditional phrases and logical constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oprot
    -0.75
     this
    -0.69
    MessageTagHelper
    -0.64
    getSystemService
    -0.56
     ervan
    -0.56
     Another
    -0.56
    CodedInputStream
    -0.55
    Another
    -0.54
     swojej
    -0.54
    '];
    
    -0.52
    POSITIVE LOGITS
     los
    1.07
     els
    0.87
     les
    0.79
     các
    0.75
     τα
    0.72
     LOS
    0.65
    Τα
    0.64
     τους
    0.63
     those
    0.63
     οι
    0.62
    Activations Density 0.074%

    No Known Activations