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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 12631
    Prev
    Next
    INDEX
    Explanations

    phrases indicating obligation or responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Життєпис
    -0.80
     مشين
    -0.73
    dersfield
    -0.67
    rawDesc
    -0.65
     مُعرِّف
    -0.65
    happened
    -0.64
     상세
    -0.64
     AssemblyTitle
    -0.63
    مصادر
    -0.63
    tencent
    -0.63
    POSITIVE LOGITS
     unable
    0.67
     able
    0.60
     tasked
    0.58
    Unable
    0.53
     obliged
    0.51
     entitled
    0.50
     confronted
    0.49
     compelled
    0.49
    unable
    0.48
     encouraged
    0.48
    Activations Density 0.586%

    No Known Activations