© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4377
    Prev
    Next
    INDEX
    Explanations

    elements and commands related to graph traversal algorithms and array manipulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quity
    -0.44
     hmot
    -0.42
     fianco
    -0.42
     międzynarod
    -0.39
     wyposaż
    -0.38
    عام
    -0.38
     srdce
    -0.38
    ikas
    -0.37
     continuación
    -0.37
     calme
    -0.37
    POSITIVE LOGITS
    StoryboardSegue
    0.93
     doInBackground
    0.86
    SourceChecksum
    0.81
    UseVisualStyle
    0.80
    memoized
    0.77
     dfs
    0.77
     useSelector
    0.76
    AnchorTagHelper
    0.76
    aarrggbb
    0.75
    蚪
    0.75
    Activations Density 0.825%

    No Known Activations