© 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. 8-GEMMASCOPE-RES-16K
    11. 5636
    Prev
    Next
    INDEX
    Explanations

    syntax related to function definitions and parameter lists in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     either
    -0.56
    ,
    -0.52
     the
    -0.49
    -
    -0.48
     to
    -0.48
     at
    -0.46
     there
    -0.46
     
    -0.45
    ron
    -0.45
     став
    -0.44
    POSITIVE LOGITS
     ExecuteAsync
    1.22
    ngOnInit
    1.12
    abestanden
    1.10
    initComponents
    1.08
     للمعارف
    1.07
    AddTagHelper
    1.05
     AssemblyCulture
    1.02
    CloseOperation
    1.02
     BoxFit
    1.01
     useHistory
    0.97
    Activations Density 0.021%

    No Known Activations