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. 1-GEMMASCOPE-RES-16K
    6. 6327
    Prev
    Next
    INDEX
    Explanations

    technical terms and elements related to software and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     better
    -0.49
     sweet
    -0.48
     toughest
    -0.48
    ارو
    -0.48
     next
    -0.48
    ัญ
    -0.47
    Better
    -0.47
    dehyde
    -0.46
     worse
    -0.46
    thym
    -0.44
    POSITIVE LOGITS
    InjectAttribute
    0.79
    expandindo
    0.78
    Portail
    0.73
    AnchorStyles
    0.71
    بوابة
    0.71
    ervlak
    0.70
    ThroughAttribute
    0.69
     cms
    0.69
     Directive
    0.69
     digress
    0.68
    Activations Density 2.177%

    No Known Activations