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. 6-GEMMASCOPE-RES-16K
    6. 13357
    Prev
    Next
    INDEX
    Explanations

    terms related to tracking or monitoring processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HasAnnotation
    -0.97
     للمعارف
    -0.95
     fermés
    -0.94
     Houſe
    -0.93
    coltura
    -0.93
    ########.
    -0.92
     Blackman
    -0.92
     duquel
    -0.91
     occhiali
    -0.90
     BorderRadius
    -0.90
    POSITIVE LOGITS
     trace
    1.90
     Trace
    1.80
    Trace
    1.71
    trace
    1.60
     traced
    1.58
     tracing
    1.54
     TRACE
    1.52
     traces
    1.51
    TRACE
    1.40
    Tracing
    1.35
    Activations Density 0.126%

    No Known Activations