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. 7-GEMMASCOPE-RES-16K
    6. 8938
    Prev
    Next
    INDEX
    Explanations

    references to the concepts of care and concern

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transfieras
    -0.55
    nall
    -0.49
    cludes
    -0.49
     Parce
    -0.47
     points
    -0.46
    gameserver
    -0.46
    写在
    -0.46
    zuma
    -0.46
    olução
    -0.46
     cares
    -0.46
    POSITIVE LOGITS
     ControllerBase
    0.66
    ammans
    0.65
    oneofs
    0.63
    
    0.61
    wijl
    0.60
    posedge
    0.60
    rzez
    0.60
    DebuggerStep
    0.60
     الحره
    0.59
    IsMutable
    0.58
    Activations Density 0.528%

    No Known Activations