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. 8538
    Prev
    Next
    INDEX
    Explanations

    specific programming or mathematical constructs and their definitions

    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
    RegistryLite
    -0.86
     â
    -0.71
    AndroidJUnit
    -0.64
    BeginInit
    -0.62
    exels
    -0.55
    Â
    -0.55
     ‚
    -0.54
     Â
    -0.52
    ="@+
    -0.50
    ATUM
    -0.49
    POSITIVE LOGITS
    Personensuche
    0.80
    تقاوى
    0.68
    Personendaten
    0.62
    Hentet
    0.60
    --)
    
    0.59
    IVEREF
    0.56
    RTEE
    0.55
    abestanden
    0.55
    .--
    0.55
    --
    0.53
    Activations Density 1.527%

    No Known Activations