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. 14-GEMMASCOPE-RES-16K
    6. 10630
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to conditionals and loops

    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
     qu
    -0.47
    .
    -0.47
     relever
    -0.45
    mybatisplus
    -0.45
     poche
    -0.44
    qu
    -0.43
    ide
    -0.43
    HALT
    -0.41
     die
    -0.41
    Heath
    -0.41
    POSITIVE LOGITS
     kasarigan
    1.17
     MainAxisSize
    0.95
     EconPapers
    0.92
     ModelExpression
    0.88
    AndEndTag
    0.82
    $")
    0.82
     كومونز
    0.81
    ]")]
    0.79
    __':
    
    0.79
    WebVitals
    0.78
    Activations Density 0.062%

    No Known Activations