© 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. 11-GEMMASCOPE-RES-16K
    6. 13013
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to medical research and pharmaceuticals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.81
    __':
    
    -0.76
    
    -0.73
    <bos>
    -0.67
    はじめに
    -0.61
    __":
    
    -0.60
    agisse
    -0.60
    __':
    -0.60
     مشين
    -0.60
    LETON
    -0.58
    POSITIVE LOGITS
     ebenfalls
    0.65
     vPvB
    0.57
    BeginInit
    0.53
    同じく
    0.51
     similaires
    0.51
    こっち
    0.49
    another
    0.49
     saluti
    0.48
     SIMILAR
    0.47
     másik
    0.47
    Activations Density 1.050%

    No Known Activations