© 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. 31-GEMMASCOPE-RES-16K
    11. 5416
    Prev
    Next
    INDEX
    Explanations

    references to governmental or authoritative entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    acronyms and abbreviations in parentheses.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ApiModelProperty
    -0.51
    
    -0.49
    erii
    -0.49
    
    -0.46
    UserScript
    -0.45
     sartén
    -0.45
    TintMode
    -0.44
    DockStyle
    -0.44
    jiet
    -0.43
     ProtoMessage
    -0.43
    POSITIVE LOGITS
     MSA
    0.77
     SSA
    0.72
     PPA
    0.67
    MSA
    0.67
    PMA
    0.66
    MPA
    0.65
     PMA
    0.65
     DCA
    0.65
     ISA
    0.64
     HSA
    0.64
    Activations Density 0.619%

    No Known Activations