© 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. 15-GEMMASCOPE-RES-16K
    6. 4904
    Prev
    Next
    INDEX
    Explanations

    references to research, education, and professional roles, particularly focusing on students, researchers, and consumers

    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
     Wasn
    -0.47
    nich
    -0.44
     coincides
    -0.44
     ánh
    -0.44
     originates
    -0.42
    tienne
    -0.41
     manzanas
    -0.41
    truncate
    -0.41
    Pale
    -0.41
    ATIV
    -0.40
    POSITIVE LOGITS
    esez
    0.74
    oredCriteria
    0.73
     lenker
    0.73
    mybatisplus
    0.73
     ddelweddau
    0.68
     мәкал
    0.66
     Савезне
    0.61
    zeba
    0.60
     iprot
    0.60
    '),
    
    0.59
    Activations Density 0.422%

    No Known Activations