Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 3511
    Prev
    Next
    INDEX
    Explanations

    references to photographic techniques and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InputBorder
    -0.86
    RectangleBorder
    -0.80
     الرياضيه
    -0.77
    ыгана
    -0.74
     anthracite
    -0.72
     ControllerBase
    -0.70
    yntaxException
    -0.70
    oneofs
    -0.68
    SharedDtor
    -0.67
    entennial
    -0.67
    POSITIVE LOGITS
    Hozzáférés
    0.56
     shooting
    0.55
     shoot
    0.51
     camera
    0.49
     Camera
    0.49
    相机
    0.48
     photographers
    0.46
     shutter
    0.45
    Shooting
    0.45
    Camera
    0.44
    Activations Density 0.619%

    No Known Activations