© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 6-GEMMASCOPE-RES-16K
    11. 5646
    Prev
    Next
    INDEX
    Explanations

    sections of text that contain the character "-" followed by a non-zero activation

    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
    sizeCache
    -1.00
     démocr
    -0.92
    $")
    -0.86
    )");
    -0.86
     ModelExpression
    -0.84
     Efq
    -0.84
     Савезне
    -0.83
     étoit
    -0.83
     étoient
    -0.83
     $_"
    -0.83
    POSITIVE LOGITS
    -
    0.64
    (
    0.59
    *
    0.52
        
    0.52
    ↵
    0.51
    –
    0.49
      
    0.49
    _
    0.48
    GenerationType
    0.47
    <eos>
    0.46
    Activations Density 0.216%

    No Known Activations