© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11929
    Prev
    Next
    INDEX
    Explanations

    concepts related to mutual benefits and positive outcomes in various contexts

    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
    cult
    -0.34
     Entwurf
    -0.33
    Handlung
    -0.33
    큼
    -0.33
    ständige
    -0.33
     tiếp
    -0.32
    nior
    -0.32
    umin
    -0.32
    います
    -0.31
    totta
    -0.31
    POSITIVE LOGITS
     ModelExpression
    0.61
    sizeCache
    0.60
    
    0.57
    rungsseite
    0.57
    WriteTagHelper
    0.55
     benefited
    0.54
    AddTagHelper
    0.52
    styleType
    0.52
     pinulongan
    0.51
    Tikang
    0.50
    Activations Density 0.180%

    No Known Activations