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. 4-GEMMASCOPE-RES-16K
    6. 3237
    Prev
    Next
    INDEX
    Explanations

    quantitative comparisons involving quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    initComponents
    -0.65
    xase
    -0.64
     فريبيس
    -0.64
    UITableViewCell
    -0.62
    })`
    -0.60
     IActionResult
    -0.59
    getMenuInflater
    -0.59
    ="&#
    -0.56
     للمعارف
    -0.56
     CEO
    -0.55
    POSITIVE LOGITS
     Censo
    0.63
    iastes
    0.61
     yli
    0.59
    য়া
    0.55
    fjspx
    0.55
     beginnetje
    0.54
     peste
    0.54
     препратки
    0.54
     past
    0.53
     ponad
    0.52
    Activations Density 0.245%

    No Known Activations