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. 12014
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal consequences and disciplinary measures

    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
     esternos
    -0.67
    ArgsConstructor
    -0.61
    esModule
    -0.59
    MockBean
    -0.59
    COUVER
    -0.57
     disponibilités
    -0.55
    cshtml
    -0.55
    tisseur
    -0.55
    InputTagHelper
    -0.54
     scher
    -0.54
    POSITIVE LOGITS
     punishment
    0.83
     punishable
    0.79
     punished
    0.78
     punishments
    0.73
     punish
    0.71
     Punishment
    0.68
     disciplinary
    0.66
     penalties
    0.64
     offenders
    0.62
     punitive
    0.61
    Activations Density 0.439%

    No Known Activations