© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 6942
    Prev
    Next
    INDEX
    Explanations

    technical terms related to 3D graphics, particularly focusing on lighting and shadow properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    less
    -0.50
    pin
    -0.49
    Skip
    -0.49
    raf
    -0.47
    Less
    -0.47
     مقاط
    -0.46
     metastasis
    -0.45
    Rea
    -0.45
    녀
    -0.44
     повіт
    -0.44
    POSITIVE LOGITS
    RectangleBorder
    0.82
    ChildScrollView
    0.81
    rrggbb
    0.78
    MLLoader
    0.77
    HasAnnotation
    0.77
    tagHelperRunner
    0.74
    stdc
    0.73
    IsContent
    0.72
    apimachinery
    0.71
    HasForeignKey
    0.70
    Activations Density 0.403%

    No Known Activations