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. 2871
    Prev
    Next
    INDEX
    Explanations

    output statements in PHP code

    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
    kyard
    -0.85
    __':
    
    -0.81
     estimés
    -0.80
    multer
    -0.80
    NOPQRST
    -0.73
     AspNetCore
    -0.73
    LookAnd
    -0.73
    ViewImports
    -0.72
    GenerationType
    -0.71
    RuleContext
    -0.70
    POSITIVE LOGITS
     Echo
    1.49
     echo
    1.42
    echo
    1.39
    Echo
    1.31
     ECHO
    1.26
    ECHO
    1.25
     Echoes
    1.23
     echoing
    1.05
     echoes
    1.04
     echoed
    0.93
    Activations Density 0.026%

    No Known Activations