© 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. 18-GEMMASCOPE-RES-16K
    11. 6836
    Prev
    Next
    INDEX
    Explanations

    references to error handling and fixing in programming contexts

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

    Text after punctuation

    np_acts-logits-general · gemini-2.0-flash

    programming context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
      
    -1.01
    </h1>
    -0.93
    </h3>
    -0.90
    </h2>
    -0.90
    <b>
    -0.86
    </b>
    -0.82
    <strong>
    -0.81
    \\
    -0.73
    ↵
    -0.67
    <sup>
    -0.66
    POSITIVE LOGITS
     كومونز
    1.15
     فريبيس
    1.10
     الرياضيه
    1.02
    TestingModule
    0.99
    NewUrlParser
    0.98
     '\\;'
    0.95
     للمعارف
    0.91
    +#+#
    0.91
    اریخ
    0.90
    BeginInit
    0.89
    Activations Density 0.034%

    No Known Activations