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. 2-GEMMASCOPE-RES-16K
    6. 6393
    Prev
    Next
    INDEX
    Explanations

    terms related to medical and scientific terminology, particularly in the context of cancer and immunology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onAttach
    -0.65
     transfieras
    -0.57
     esboço
    -0.55
    ếng
    -0.51
    ']))
    
    -0.51
    )$/,
    -0.49
     ProtoMessage
    -0.48
    astronomie
    -0.48
    InjectAttribute
    -0.48
     članak
    -0.47
    POSITIVE LOGITS
    MC
    1.47
     MC
    1.43
    FC
    1.38
    RC
    1.32
    mc
    1.28
     FC
    1.25
     RC
    1.25
     mc
    1.23
     LC
    1.23
     HC
    1.20
    Activations Density 2.723%

    No Known Activations