© 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. 20-GEMMASCOPE-RES-16K
    6. 15670
    Prev
    Next
    INDEX
    Explanations

    negative phrases or words indicating limitations or issues related to systems or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ormais
    -0.47
    กรม
    -0.40
    GraphicsUnit
    -0.39
    ervant
    -0.39
     Horowitz
    -0.38
    MemoryWarning
    -0.38
    rhein
    -0.38
    ATHER
    -0.38
     utmost
    -0.36
     Lawler
    -0.36
    POSITIVE LOGITS
     للاسماء
    0.69
     transférez
    0.64
     utafitiHapana
    0.51
     समीक्षाओं
    0.44
     nahilalakip
    0.40
    logna
    0.39
     Bioaccumulative
    0.39
    клопе
    0.36
    SpringBootTest
    0.36
     UIKit
    0.36
    Activations Density 0.419%

    No Known Activations