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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 3156
    Prev
    Next
    INDEX
    Explanations

    variables or functions indicating an object's state or properties

    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
     raiſ
    -0.94
     Theſe
    -0.87
     Houſe
    -0.86
     ſever
    -0.82
     ་་
    -0.82
     houſe
    -0.81
     photolibrary
    -0.78
     ―――――
    -0.78
     doubtnut
    -0.77
     themſelves
    -0.77
    POSITIVE LOGITS
     Is
    1.36
     is
    1.29
     IS
    1.24
    Is
    1.23
    is
    0.96
     Has
    0.96
    Has
    0.86
     has
    0.81
     setIs
    0.81
    IS
    0.80
    Activations Density 0.085%

    No Known Activations