© 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. 6-GEMMASCOPE-RES-16K
    6. 13297
    Prev
    Next
    INDEX
    Explanations

    references to data structures and object configurations

    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
    <eos>
    -0.44
    at
    -0.43
    zí
    -0.40
     Signalez
    -0.40
    들의
    -0.39
    そういった
    -0.39
                                   
    -0.38
     profitably
    -0.38
    이나
    -0.37
                
    -0.37
    POSITIVE LOGITS
     Мексичка
    0.90
     שוליים
    0.84
    principalColumn
    0.80
     jspb
    0.79
     الرياضيه
    0.78
    dafx
    0.74
    formik
    0.74
    सन्दर्भ
    0.72
    談社
    0.72
     PeEnEo
    0.71
    Activations Density 0.960%

    No Known Activations