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. 17-GEMMASCOPE-RES-16K
    6. 403
    Prev
    Next
    INDEX
    Explanations

    elements related to programming or code structure, particularly focusing on loading and managing resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.56
     المعيارى
    -0.55
    opsida
    -0.49
    </i>
    -0.49
     
    -0.46
    abstractmethod
    -0.45
     modo
    -0.43
     Meksiku
    -0.43
     transfieras
    -0.42
    tagHelper
    -0.42
    POSITIVE LOGITS
     itſelf
    1.03
     myſelf
    0.94
     himſelf
    0.79
     EconPapers
    0.78
     Eſ
    0.77
    Numerology
    0.76
     Préférences
    0.75
    Geplaatst
    0.75
     doccia
    0.73
     Tatsache
    0.73
    Activations Density 1.408%

    No Known Activations