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. 1-GEMMASCOPE-RES-16K
    6. 13543
    Prev
    Next
    INDEX
    Explanations

    technical terms related to medical and biological contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ếng
    -0.60
     Correia
    -0.56
     Früchte
    -0.52
     ITIS
    -0.52
     throw
    -0.52
    ﴿
    -0.52
    Yosh
    -0.52
     contextLoads
    -0.51
    setcounter
    -0.50
     Dae
    -0.50
    POSITIVE LOGITS
    énario
    0.74
    FieldDescriptor
    0.63
    __':
    
    0.60
    Vidite
    0.57
     parade
    0.57
    ballet
    0.55
     Parade
    0.55
     Signalez
    0.55
    bbene
    0.54
     arbit
    0.54
    Activations Density 2.482%

    No Known Activations