© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 4964
    Prev
    Next
    INDEX
    Explanations

    sections of text that describe functionality and implementation details

    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
    TextSpan
    -0.60
     Efq
    -0.56
     mapStateToProps
    -0.55
     Reſ
    -0.55
     photolibrary
    -0.55
     RoutedEventArgs
    -0.54
     IndexError
    -0.54
     Majefty
    -0.52
     contextLoads
    -0.51
     aVar
    -0.51
    POSITIVE LOGITS
     optionally
    0.66
     Infórmanos
    0.65
    vably
    0.60
    AddTagHelper
    0.60
     Normdatei
    0.60
     оригіналу
    0.59
    racite
    0.59
     défaut
    0.58
     todo
    0.55
     default
    0.55
    Activations Density 0.919%

    No Known Activations