© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 3890
    Prev
    Next
    INDEX
    Explanations

    technical terminology and specific identifiers related to coding and legal frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 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
    addCriterion
    -4.06
    Aholisi
    -0.37
    Rcpp
    -0.32
     &___
    -0.31
     ambas
    -0.30
     płyn
    -0.30
     setuptools
    -0.30
    NameInMap
    -0.30
     Tuhan
    -0.28
    ądze
    -0.28
    POSITIVE LOGITS
    ValueStyle
    5.00
    ScopeManager
    4.56
    GraphicsUnit
    2.83
    AnchorStyles
    1.23
    SourceChecksum
    1.21
    tagHelperRunner
    1.16
    SequentialGroup
    1.01
    AddTagHelper
    0.98
    ContentAsync
    0.96
     wireType
    0.96
    Activations Density 0.007%

    No Known Activations