© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 10009
    Prev
    Next
    INDEX
    Explanations

    phrases indicating data or quantities related to physical processes or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.81
     oprot
    -0.81
    SourceChecksum
    -0.75
    Kaynakça
    -0.74
    pushFollow
    -0.71
    DebuggerNonUser
    -0.69
    Portale
    -0.65
    ########.
    -0.65
     iprot
    -0.64
    évaluateur
    -0.60
    POSITIVE LOGITS
     fill
    3.36
     filling
    3.34
     fills
    3.08
     Fill
    3.00
     Filling
    2.99
    fill
    2.94
    Filling
    2.91
    Fill
    2.91
     filled
    2.90
     FILL
    2.81
    Activations Density 0.572%

    No Known Activations