© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 6-GEMMASCOPE-RES-16K
    11. 5105
    Prev
    Next
    INDEX
    Explanations

    instances of the word "right" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     McKinnon
    -1.00
    __":
    -0.90
    oredCriteria
    -0.87
    ecd
    -0.85
    matchCondition
    -0.84
    Autoritní
    -0.84
     tartalomajánló
    -0.84
     <<<<<<<<<<<<<<
    -0.82
    期刊论文
    -0.82
    CMYK
    -0.81
    POSITIVE LOGITS
    right
    1.70
     right
    1.66
     RIGHT
    1.61
     Right
    1.60
    Right
    1.57
    RIGHT
    1.50
    setRight
    1.23
     righ
    1.20
    getRight
    1.18
     Righ
    1.11
    Activations Density 0.095%

    No Known Activations