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. 16-GEMMASCOPE-RES-16K
    6. 14787
    Prev
    Next
    INDEX
    Explanations

    phrases related to rights and privileges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Legal and human "rights"

    np_acts-logits-general · gemini-2.0-flash

    right to or rights of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rogels
    -0.85
    IUrlHelper
    -0.83
    }{*}{}
    -0.79
    awaiter
    -0.78
     surla
    -0.77
     تكبرها
    -0.77
    :✨
    -0.74
    </table>
    -0.74
     ostavi
    -0.73
    ագրություններ
    -0.73
    POSITIVE LOGITS
     rights
    0.99
     Rights
    0.86
     RIGHTS
    0.81
    Rights
    0.79
    rights
    0.79
     derechos
    0.66
     direitos
    0.66
     diritti
    0.62
     права
    0.53
     Rechte
    0.53
    Activations Density 0.145%

    No Known Activations