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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 15114
    Prev
    Next
    INDEX
    Explanations

    references to the NHS (National Health Service) and its associated programs or services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Millard
    -0.72
    المناصب
    -0.72
    MethodType
    -0.72
    minLength
    -0.71
    PostMapping
    -0.71
     Persons
    -0.71
    LookAnd
    -0.70
    /**
    -0.69
    Abitanti
    -0.69
     cust
    -0.68
    POSITIVE LOGITS
     carrots
    0.82
    "])
    
    0.81
    ,:),
    0.80
     Carrots
    0.78
    Carrot
    0.77
    "]);
    
    0.77
    "><?=
    0.76
    exao
    0.76
    )))));
    0.75
    Deps
    0.73
    Activations Density 0.028%

    No Known Activations