© 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. 33-GEMMASCOPE-RES-16K
    6. 8329
    Prev
    Next
    INDEX
    Explanations

    technical terms and functions related to data handling and model processing in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    المشاركات
    -0.40
     "..\..\
    -0.32
    verifyException
    -0.30
     refinance
    -0.30
    EventQueue
    -0.29
     "..\..\..\
    -0.29
    antwoorden
    -0.29
    コミ
    -0.29
     ujednoznacz
    -0.28
    ukone
    -0.28
    POSITIVE LOGITS
     torch
    0.94
    torch
    0.82
     Torch
    0.71
    Torch
    0.70
     torches
    0.65
     TOR
    0.62
     torchvision
    0.61
     invokingState
    0.60
    TOR
    0.60
    makeText
    0.57
    Activations Density 0.095%

    No Known Activations