© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8810
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "mine"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.60
    BeginContext
    -0.57
    AddHtmlAttribute
    -0.57
    ôtel
    -0.56
     betweenstory
    -0.54
    adaptiveStyles
    -0.53
     nahilalakip
    -0.53
     raiſ
    -0.52
    ScopeManager
    -0.51
     onCreateView
    -0.49
    POSITIVE LOGITS
     mine
    3.41
     Mine
    2.91
    Mine
    2.84
    mine
    2.58
     MINE
    2.52
     mines
    2.45
    MINE
    2.17
     mining
    1.93
     Mines
    1.91
     mined
    1.88
    Activations Density 0.131%

    No Known Activations