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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 15613
    Prev
    Next
    INDEX
    Explanations

    phrases indicating variability or dependency based on specific conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding "depends" or "depending"

    np_acts-logits-general · gemini-2.0-flash

    it depends

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \{\\
    -0.58
     []),
    -0.56
    στημα
    -0.55
    ]='\
    -0.54
    MockMvc
    -0.53
     TResult
    -0.51
    nativeElement
    -0.51
    ogie
    -0.51
    licó
    -0.50
    Predecesor
    -0.49
    POSITIVE LOGITS
     depends
    3.17
     depending
    3.12
     depend
    2.96
    depending
    2.76
     Depends
    2.73
     depended
    2.73
    depends
    2.65
     dependent
    2.61
    Depends
    2.54
     dépend
    2.44
    Activations Density 0.755%

    No Known Activations