© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 8397
    Prev
    Next
    INDEX
    Explanations

    references to different stages or phases in a process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vacunas
    -0.48
     doméstico
    -0.44
     electricidad
    -0.44
     Política
    -0.44
     elétrica
    -0.43
     keramik
    -0.43
     internetu
    -0.43
    ioutil
    -0.43
     corporativa
    -0.42
     suara
    -0.42
    POSITIVE LOGITS
     stage
    1.89
     Stage
    1.83
    Stage
    1.73
     STAGE
    1.70
    stage
    1.66
     stages
    1.64
     Stages
    1.51
    STAGE
    1.47
    Stages
    1.45
    stages
    1.43
    Activations Density 0.167%

    No Known Activations