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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 4008
    Prev
    Next
    INDEX
    Explanations

    terms related to collection and accumulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SBATCH
    -0.91
     AssemblyCulture
    -0.85
    Зноскі
    -0.84
     ReactDOM
    -0.84
    UseVisualStyle
    -0.82
     Réponses
    -0.79
    IntoConstraints
    -0.79
    didSet
    -0.79
    aarrggbb
    -0.77
    DebuggerStep
    -0.77
    POSITIVE LOGITS
     collection
    1.30
     Collect
    1.29
     collections
    1.28
    Collect
    1.27
     COLLECT
    1.25
    COLLECT
    1.25
     collecting
    1.23
     collects
    1.20
     Collecting
    1.20
     collectors
    1.20
    Activations Density 0.209%

    No Known Activations