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. 10-GEMMASCOPE-RES-16K
    6. 4699
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and operators used in equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     WIC
    -0.81
    Hob
    -0.78
    aneous
    -0.76
    Cesar
    -0.75
     prostagland
    -0.74
     HAC
    -0.74
     Hock
    -0.74
     Demp
    -0.73
    ervlak
    -0.71
    Marcia
    -0.70
    POSITIVE LOGITS
    _{\
    1.37
     _{\
    1.03
    }_{\
    0.99
     }_{\
    0.91
    ]_{\
    0.90
    )_{\
    0.88
    zeria
    0.84
    '){
    
    0.81
    }}_{\
    0.79
    ()){
    
    0.78
    Activations Density 0.178%

    No Known Activations