© 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-2-9B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 8231
    Prev
    Next
    INDEX
    Explanations

    terms related to performance evaluation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iseite
    -0.42
    glLoad
    -0.39
    SourceChecksum
    -0.37
     istore
    -0.37
    spyOn
    -0.35
     obstante
    -0.35
     jā
    -0.35
     Arun
    -0.35
     Premio
    -0.34
    綬
    -0.34
    POSITIVE LOGITS
     leſs
    0.59
    AnchorStyles
    0.59
     very
    0.59
    CrossRef
    0.57
     zijne
    0.57
    WebServlet
    0.55
     much
    0.51
     itſelf
    0.50
    做得
    0.50
     less
    0.49
    Activations Density 0.520%

    No Known Activations