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. 2-GEMMASCOPE-RES-16K
    6. 4099
    Prev
    Next
    INDEX
    Explanations

    references to HTML documents and their structural components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.59
    لیس
    -0.55
     M
    -0.50
     u
    -0.47
     I
    -0.47
     soon
    -0.43
    )
    -0.42
    Enumerator
    -0.42
    M
    -0.42
     D
    -0.42
    POSITIVE LOGITS
    __":
    
    1.21
    onViewCreated
    1.18
    __':
    1.16
    __':
    
    1.13
    UnitTesting
    1.13
    StoryboardSegue
    1.12
    __":
    1.11
     onCreateView
    1.10
     AppComponent
    1.10
    viewDidLoad
    1.07
    Activations Density 0.385%

    No Known Activations