© 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. 34-GEMMASCOPE-RES-16K
    11. 6164
    Prev
    Next
    INDEX
    Explanations

    machinery and equipment used in construction and industrial operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     poiv
    -0.37
     HasFactory
    -0.34
    unary
    -0.33
    Parcelize
    -0.32
    Wra
    -0.31
     persegu
    -0.31
    WebVitals
    -0.31
     serde
    -0.31
    mnop
    -0.31
    arne
    -0.30
    POSITIVE LOGITS
     digging
    1.70
     exca
    1.51
     excavation
    1.48
     dug
    1.46
    exca
    1.40
     excav
    1.38
     excavated
    1.38
    Exca
    1.31
     digger
    1.28
     dig
    1.27
    Activations Density 0.347%

    No Known Activations