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. 20-GEMMASCOPE-RES-16K
    6. 5259
    Prev
    Next
    INDEX
    Explanations

    phrases indicating causation or factors contributing to outcomes

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

    "In part" or "due to" phrases

    np_acts-logits-general · gemini-2.0-flash

    due in part to

    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
     EconPapers
    -0.99
    ]")]
    -0.95
    WebVitals
    -0.89
     مشين
    -0.88
    rungsseite
    -0.86
    DockStyle
    -0.84
    
    -0.84
     MessageBoxIcon
    -0.84
     myſelf
    -0.83
    ModelAdmin
    -0.82
    POSITIVE LOGITS
     partly
    1.94
     partially
    1.85
    partly
    1.58
     Partially
    1.37
     Partly
    1.35
     largely
    1.31
     partial
    1.18
    Partly
    1.15
    parti
    1.13
     parcialmente
    1.11
    Activations Density 0.350%

    No Known Activations