© 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. 39-GEMMASCOPE-RES-16K
    11. 3150
    Prev
    Next
    INDEX
    Explanations

    concepts related to authority and function

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     می
    -1.03
     برانيه
    -0.78
     ==
    -0.73
    事が
    -0.67
    protoimpl
    -0.66
    事を
    -0.65
     نمی
    -0.65
     المعيارى
    -0.64
     мәкал
    -0.64
    webElementGuid
    -0.63
    POSITIVE LOGITS
    −
    0.36
    首
    0.35
     −
    0.32
    IZER
    0.31
     ===
    0.30
    IZATION
    0.30
     className
    0.29
     tab
    0.28
     पहु
    0.28
     económico
    0.28
    Activations Density 0.290%

    No Known Activations