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. 4716
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and attributes associated with data structures and handling, particularly focusing on skills and actions in a coding context

    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
     للاسماء
    -0.58
    ++)
    
    -0.57
    "]=
    -0.53
    acyjnych
    -0.53
    haden
    -0.52
    انيف
    -0.51
    adaptiveStyles
    -0.51
    }])
    -0.50
    icznego
    -0.50
    ")));
    
    -0.50
    POSITIVE LOGITS
     nakalista
    0.81
    +#+#
    0.74
    ContentAsync
    0.66
    tableFuture
    0.63
     AppBundle
    0.61
    principalColumn
    0.61
    Παραπομπές
    0.59
    apimachinery
    0.58
     AspNetCore
    0.57
    ConstraintMaker
    0.57
    Activations Density 0.397%

    No Known Activations