© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 7133
    Prev
    Next
    INDEX
    Explanations

    instances of the word "review" and its derivatives in various contexts

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

    "Review" or related scientific publications

    np_acts-logits-general · gemini-2.0-flash

    review preceding of or specific contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     getY
    -0.61
     ausz
    -0.57
    ICATION
    -0.56
    ματο
    -0.55
    imagePath
    -0.54
     imagePath
    -0.53
    ष्ठ
    -0.53
     Dallas
    -0.53
    icoot
    -0.52
     am
    -0.52
    POSITIVE LOGITS
    PhysRev
    1.05
     Reviews
    1.04
    Reviews
    0.99
    REVIEW
    0.97
     Review
    0.96
     REVIEWS
    0.96
     REVIEW
    0.93
     reviews
    0.93
    Review
    0.90
    review
    0.89
    Activations Density 0.100%

    No Known Activations