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. 8571
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to casual work attire and professional settings

    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
     E
    -0.43
    NameInMap
    -0.42
    STRU
    -0.38
    E
    -0.37
    бурге
    -0.37
    侯
    -0.36
     anticipation
    -0.36
    Tr
    -0.36
    ..
    -0.36
    想
    -0.36
    POSITIVE LOGITS
    DockStyle
    0.89
     kasarigan
    0.79
    Билгалдахарш
    0.77
    addPreferredGap
    0.74
    Skocz
    0.73
    Viitteet
    0.70
    brainly
    0.69
     Vikipedi
    0.69
     BoxFit
    0.69
     occaf
    0.68
    Activations Density 0.261%

    No Known Activations