© 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. 36-GEMMASCOPE-RES-16K
    11. 14775
    Prev
    Next
    INDEX
    Explanations

    structured data or references to figures and statistical models in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -0.58
     AssemblyProduct
    -0.53
     الحره
    -0.52
    WriteTagHelper
    -0.51
    évaluateur
    -0.51
    Nationalité
    -0.47
    ----</
    -0.43
    MessageTagHelper
    -0.43
     resourceCulture
    -0.43
     ujednoznacz
    -0.40
    POSITIVE LOGITS
     CreateTagHelper
    0.68
    ValueStyle
    0.66
    tagHelperRunner
    0.65
    сылкі
    0.60
    +#+#
    0.55
     surla
    0.55
    Kariera
    0.51
    mybatisplus
    0.48
    CppMethod
    0.44
    Välislingid
    0.44
    Activations Density 3.808%

    No Known Activations