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. 14-GEMMASCOPE-RES-16K
    6. 10700
    Prev
    Next
    INDEX
    Explanations

    expressions related to function calls and control flow in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Externí
    -0.70
    правля
    -0.63
    sian
    -0.63
     Osw
    -0.63
    ฝ
    -0.62
    cey
    -0.62
     irq
    -0.61
     AppCompat
    -0.60
    tinyos
    -0.59
     operation
    -0.58
    POSITIVE LOGITS
    __':
    
    1.25
    __":
    1.18
    __':
    1.15
    __":
    
    1.13
    ]")]
    0.75
     ModelExpression
    0.73
    ])]
    0.73
    ']))
    0.72
    '])){
    0.70
     {
    0.69
    Activations Density 0.085%

    No Known Activations