© 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. 8-GEMMASCOPE-RES-16K
    6. 15307
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts from computational mathematics and programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verwijspagina
    -0.66
    <?
    -0.53
    Джерела
    -0.52
    nextInt
    -0.47
     înc
    -0.45
     createContext
    -0.44
     veux
    -0.44
     SSSR
    -0.43
     useContext
    -0.43
    KATH
    -0.42
    POSITIVE LOGITS
     utafitiHapana
    0.72
    RenderAtEndOf
    0.68
    ']],
    0.66
    uzzi
    0.65
    "];
    
    0.64
    ")));
    
    0.64
    исленность
    0.62
    Rè
    0.62
    ftagPool
    0.62
     otomatig
    0.60
    Activations Density 1.392%

    No Known Activations