© 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. 15-GEMMASCOPE-RES-16K
    11. 1956
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental conditions and factors affecting biological selection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArrowToggle
    -0.61
    arXiv
    -0.59
    клопе
    -0.58
    wikimedia
    -0.58
    KindOfClass
    -0.57
    troppo
    -0.56
    mybatisplus
    -0.56
     REPUBLIC
    -0.56
    PECT
    -0.56
    ímite
    -0.55
    POSITIVE LOGITS
    aarrggbb
    0.54
    ustra
    0.46
    kulum
    0.45
     personlig
    0.44
     становника
    0.43
    UTERS
    0.43
    ThroughAttribute
    0.43
    個人
    0.42
    IUrlHelper
    0.41
     psycopg
    0.40
    Activations Density 1.434%

    No Known Activations