Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 92299
    Prev
    Next
    INDEX
    Explanations

    terms and phrases associated with error handling and exit statuses in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    error exit codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.81
    AndEndTag
    -0.79
    __':
    
    -0.73
     للمعارف
    -0.69
    tvguidetime
    -0.67
    OGND
    -0.63
    ]")]
    -0.63
    matchCondition
    -0.62
    RectangleBorder
    -0.62
    ChildScrollView
    -0.62
    POSITIVE LOGITS
     hidrá
    0.31
     neceff
    0.29
    .
    0.28
    jeka
    0.28
    1
    0.28
    FAILURE
    0.28
    ztat
    0.27
     мора
    0.27
    detectChanges
    0.27
    OK
    0.27
    Activations Density 0.005%

    No Known Activations