© 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. 16-GEMMASCOPE-RES-16K
    11. 8699
    Prev
    Next
    INDEX
    Explanations

    code snippets and syntax in programming-related text

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

    Code snippets or code-related content

    np_acts-logits-general · gemini-2.0-flash

    da Silva, 事がある

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Loft
    -0.49
     standard
    -0.46
     Extended
    -0.45
     étend
    -0.44
    rella
    -0.44
    Extended
    -0.43
    ين
    -0.43
    <b>
    -0.42
    Loft
    -0.42
    неопр
    -0.41
    POSITIVE LOGITS
     '\\;'
    1.05
    GEBURTSDATUM
    0.96
    rungsseite
    0.93
     NSCoder
    0.91
     disambiguazione
    0.91
     дописавши
    0.83
    tagHelperRunner
    0.83
     surla
    0.82
    
    0.81
    RenderAtEndOf
    0.81
    Activations Density 0.061%

    No Known Activations