© 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. 21-GEMMASCOPE-RES-16K
    6. 12210
    Prev
    Next
    INDEX
    Explanations

    coding constructs related to method and property declarations in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    м
    -0.66
    balleur
    -0.56
    –
    -0.54
     ddelweddau
    -0.53
    GeneratedMessage
    -0.53
    G
    -0.52
    й
    -0.51
    م
    -0.50
    er
    -0.50
    SP
    -0.50
    POSITIVE LOGITS
     propOrder
    0.74
    istoitu
    0.64
     colorés
    0.61
    BoxLayout
    0.58
    nasium
    0.57
    Wymiary
    0.57
    URIComponent
    0.57
    LEIA
    0.56
    NameInMap
    0.56
    ʁ
    0.56
    Activations Density 0.024%

    No Known Activations