© 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. 8870
    Prev
    Next
    INDEX
    Explanations

    error handling and debug statements in code

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

    Code-related terms and programming keywords

    np_acts-logits-general · gemini-2.0-flash

    code```

    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
    WebElementEntity
    -1.04
     resourceCulture
    -0.96
    Hentet
    -0.85
    IsContent
    -0.82
    Personendaten
    -0.81
    XmlAccessType
    -0.80
    MigrationBuilder
    -0.79
    كويكب
    -0.78
     /\.
    -0.76
     '{@
    -0.75
    POSITIVE LOGITS
    printStackTrace
    2.22
    ↵↵↵
    0.57
     public
    0.49
    cstring
    0.48
     Obrador
    0.48
     viewDidLoad
    0.46
     print
    0.45
     getchar
    0.45
    erial
    0.45
    getTime
    0.44
    Activations Density 0.014%

    No Known Activations