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. 13-GEMMASCOPE-RES-16K
    6. 9666
    Prev
    Next
    INDEX
    Explanations

    terms related to sensitivity in various contexts, particularly in relation to biological and electronic systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lot
    -0.68
     divertimento
    -0.62
     Crowley
    -0.61
     posta
    -0.60
    Tow
    -0.59
    lot
    -0.59
     Fact
    -0.59
    KEEP
    -0.58
    หม
    -0.58
    кто
    -0.58
    POSITIVE LOGITS
     Sensitive
    1.55
     sensitive
    1.55
    Sensitive
    1.47
     sensitivity
    1.43
     sensi
    1.42
     vulnerability
    1.36
     sensitivities
    1.35
    sensitive
    1.29
     Sensitivity
    1.27
    Sensi
    1.23
    Activations Density 0.196%

    No Known Activations