© 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. 30-GEMMASCOPE-RES-16K
    11. 11013
    Prev
    Next
    INDEX
    Explanations

    phrases related to material properties and degradation

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

    Corrosion/deterioration and related processes

    np_acts-logits-general · gemini-2.0-flash

    corrosion and deterioration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/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.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enderror
    -0.42
     autorytatywna
    -0.40
    DidChange
    -0.37
    Experiment
    -0.35
     enfans
    -0.34
    yntaxException
    -0.33
    ufige
    -0.33
     Dyer
    -0.33
     mash
    -0.33
    recated
    -0.32
    POSITIVE LOGITS
     corrosion
    0.75
    corrosion
    0.69
    Corrosion
    0.67
     Corrosion
    0.65
     deterioration
    0.63
     corro
    0.60
    ThroughAttribute
    0.58
    腐
    0.57
     Weib
    0.57
     Defect
    0.55
    Activations Density 0.706%

    No Known Activations