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. 3-GEMMASCOPE-RES-16K
    6. 12434
    Prev
    Next
    INDEX
    Explanations

    references to different layers in a system or structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MHD
    -0.78
    TagMode
    -0.73
     weevil
    -0.73
     tilbake
    -0.67
    DotNetBar
    -0.67
     Weich
    -0.67
     ISNI
    -0.66
     politiet
    -0.66
     precisione
    -0.65
     riconoscimento
    -0.65
    POSITIVE LOGITS
     layer
    3.41
     Layer
    3.33
     layers
    3.27
    Layer
    3.12
     Layers
    3.11
    layer
    3.10
     LAYER
    3.06
    Layers
    2.79
    layers
    2.76
    LAYER
    2.63
    Activations Density 0.071%

    No Known Activations