© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 10501
    Prev
    Next
    INDEX
    Explanations

    phrases indicating contexts or settings of actions

    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
     betweenstory
    -0.92
    RectangleBorder
    -0.83
     myſelf
    -0.79
     wikipagina
    -0.77
    Personensuche
    -0.76
     themſelves
    -0.76
    $.
    
    -0.75
     Chriftian
    -0.75
     Houſe
    -0.75
     Monfieur
    -0.75
    POSITIVE LOGITS
    たまた
    0.65
    WillAppear
    0.59
    #+#
    0.57
     Yee
    0.51
    ,-
    0.50
    In
    0.50
    du
    0.49
    by
    0.48
    InstrumentedTest
    0.47
    .$,
    0.47
    Activations Density 0.304%

    No Known Activations