© 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. 9-GEMMASCOPE-RES-16K
    6. 217
    Prev
    Next
    INDEX
    Explanations

    references to readers and their engagement with the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #
    -0.78
     CreateTagHelper
    -0.76
    ValueStyle
    -0.67
    pox
    -0.66
    тельство
    -0.65
    ecore
    -0.63
    InjectAttribute
    -0.61
     GenerationType
    -0.60
     coraggio
    -0.60
    WithMany
    -0.60
    POSITIVE LOGITS
     readers
    1.41
     Readers
    1.38
     Reader
    1.31
     reader
    1.29
    Readers
    1.21
     viewers
    1.19
     viewer
    1.17
    readers
    1.16
     READER
    1.15
    Reader
    1.12
    Activations Density 0.121%

    No Known Activations