Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 1598
    Prev
    Next
    INDEX
    Explanations

    titles and roles related to leadership positions in organizations

    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
    ValueStyle
    -0.70
    )':
    -0.61
     وتسجيلات
    -0.60
    }`}
    -0.59
     []).
    -0.59
     isNameExpr
    -0.57
    "):
    
    -0.57
    lawesi
    -0.56
    )$_
    -0.56
    이션
    -0.56
    POSITIVE LOGITS
     assolu
    0.73
    director
    0.61
     director
    0.60
     assoluto
    0.60
    MockBean
    0.58
     CanadaChoose
    0.55
    越好
    0.54
     emeritus
    0.54
     absoluta
    0.54
     fondateur
    0.54
    Activations Density 0.067%

    No Known Activations