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. 15-GEMMASCOPE-RES-16K
    6. 8790
    Prev
    Next
    INDEX
    Explanations

    references to environmental safety and protection measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ferons
    -0.65
     مشين
    -0.63
     continúas
    -0.58
     SEDS
    -0.57
     capuche
    -0.55
     firent
    -0.52
    msgSender
    -0.51
     défaut
    -0.51
     mourut
    -0.50
     célè
    -0.50
    POSITIVE LOGITS
     fragile
    1.01
     sensitive
    0.99
     delicate
    0.95
     Sensitive
    0.82
     empfind
    0.77
     sensibles
    0.76
    sensitive
    0.75
     sensitivities
    0.73
     precious
    0.71
     frág
    0.69
    Activations Density 0.363%

    No Known Activations