Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 11889
    Prev
    Next
    INDEX
    Explanations

    specific teams, players, and sports-related terms within a sports context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewImports
    -0.71
     rentrée
    -0.59
    BeginInit
    -0.59
    发表于
    -0.58
    RemoteException
    -0.56
    Життєпис
    -0.55
     pubblicazione
    -0.55
     decât
    -0.53
     gravedad
    -0.53
     bambou
    -0.53
    POSITIVE LOGITS
    醐
    0.70
    openqa
    0.60
    JAXB
    0.54
    ,:);
    0.53
    chaffung
    0.53
    ocere
    0.52
    IContainer
    0.52
    serviceWorker
    0.51
     Elon
    0.50
    ])).
    0.49
    Activations Density 0.564%

    No Known Activations