© 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. 4-GEMMASCOPE-RES-16K
    6. 3674
    Prev
    Next
    INDEX
    Explanations

    chemical elements and compounds related to materials and solutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adaptiveStyles
    -0.91
     snippetHide
    -0.90
    
    -0.84
    
    -0.74
    AutoField
    -0.70
    InSection
    -0.70
     ब्रेकडाउन
    -0.68
    ########.
    -0.66
    省市镇
    -0.64
     nahilalakip
    -0.62
    POSITIVE LOGITS
     Na
    1.09
     Sodium
    1.01
    Sodium
    1.01
    Na
    0.99
     sodium
    0.94
    sodium
    0.92
    assium
    0.82
     sodio
    0.79
     alkali
    0.70
     Potassium
    0.70
    Activations Density 0.591%

    No Known Activations