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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 13986
    Prev
    Next
    INDEX
    Explanations

    terms related to sensitivity and specificity in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    נטרנט
    -0.52
     upor
    -0.47
    ancestor
    -0.44
    åk
    -0.43
    SOUNDBITE
    -0.43
     iVar
    -0.43
     Crow
    -0.42
    UMES
    -0.42
    ipedi
    -0.42
     engan
    -0.42
    POSITIVE LOGITS
     Sensitive
    1.70
     sensitive
    1.70
    Sensitive
    1.61
     delicate
    1.58
     sensitivity
    1.39
    sensitive
    1.39
     fragile
    1.38
     tender
    1.38
     sensitivities
    1.33
     Sensitivity
    1.29
    Activations Density 0.420%

    No Known Activations