© 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. 0-GEMMASCOPE-RES-16K
    6. 10006
    Prev
    Next
    INDEX
    Explanations

    the beginning of sentences or new thoughts in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     also
    -1.03
     protoimpl
    -0.94
     and
    -0.88
     or
    -0.87
     […]
    -0.84
     @"/
    -0.83
     his
    -0.83
     a
    -0.82
     be
    -0.82
    ;
    
    -0.81
    POSITIVE LOGITS
    <bos>
    2.35
     Shakspeare
    1.01
     itſelf
    0.99
     Monfieur
    0.96
     Theſe
    0.95
     myſelf
    0.94
     Савезне
    0.93
     negroes
    0.88
     Anſ
    0.88
     Мексичка
    0.86
    Activations Density 1.276%

    No Known Activations