© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 8807
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to nickel recovery processes from sulfide ores

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

    before "as" or related to mining

    np_acts-logits-general · gemini-2.0-flash

    mining and related words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    styleType
    -0.48
     Küchen
    -0.40
    inflater
    -0.40
     bluzka
    -0.39
     skå
    -0.39
    Šaltiniai
    -0.39
    anthemum
    -0.38
    gnan
    -0.38
     Carousel
    -0.37
     coussin
    -0.37
    POSITIVE LOGITS
     mining
    1.09
     Mining
    1.03
    Mining
    0.96
     MINING
    0.91
    mining
    0.88
     miners
    0.84
     mine
    0.83
     mined
    0.81
     miner
    0.80
     mines
    0.76
    Activations Density 0.209%

    No Known Activations