© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 3273
    Prev
    Next
    INDEX
    Explanations

    instances of the word "stdio" and evaluate the presence of conditional phrases about capability and failure in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AspNetCore
    -0.81
     BoxDecoration
    -0.78
    MENAFN
    -0.73
    jména
    -0.67
    odotus
    -0.66
    PRNewswire
    -0.64
     تضيفلها
    -0.64
    ADIAN
    -0.62
    нциклопедия
    -0.62
     anteriore
    -0.61
    POSITIVE LOGITS
    SequentialGroup
    1.04
    Must
    0.84
    xaml
    0.77
    stdio
    0.71
    must
    0.68
     Must
    0.67
     <>",
    0.64
    かれています
    0.61
    वाल
    0.60
     '{@
    0.60
    Activations Density 0.020%

    No Known Activations