Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 6169
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax, especially involving functions, data types, and error handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ly
    -0.45
      
    -0.44
    will
    -0.43
    TabStop
    -0.40
    set
    -0.38
    No
    -0.38
    太
    -0.37
     idén
    -0.37
    tech
    -0.36
    бера
    -0.36
    POSITIVE LOGITS
    SequentialGroup
    1.08
     snippetHide
    0.87
    RectangleBorder
    0.79
    ագրություններ
    0.79
    RetentionPolicy
    0.75
    ScopeManager
    0.74
    __':
    
    0.74
    ReusableCell
    0.72
    MemoryWarning
    0.72
    writerow
    0.72
    Activations Density 0.331%

    No Known Activations